Showing 1–50 of 68 results for author: Martinez, C

LACIN: Linearly Arranged Complete Interconnection Networks

Authors: Ramón Beivide, Cristóbal Camarero, Carmen Martínez, Enrique Vallejo, Mateo Valero

Abstract: Several interconnection networks are based on the complete graph topology. Networks with a moderate size can be based on a single complete graph. However, large-scale networks such as Dragonfly and HyperX use, respectively, a hierarchical or a multi-dimensional composition of complete graphs. The number of links in these networks is huge and grows rapidly with their size. This paper introduces L… ▽ More Several interconnection networks are based on the complete graph topology. Networks with a moderate size can be based on a single complete graph. However, large-scale networks such as Dragonfly and HyperX use, respectively, a hierarchical or a multi-dimensional composition of complete graphs. The number of links in these networks is huge and grows rapidly with their size. This paper introduces LACIN, a set of complete graph implementations that use identically indexed ports to link switches. This way of implementing the network reduces the complexity of its cabling and its routing. LACIN eases the deployment of networks for parallel computers of different scales, from VLSI systems to the largest supercomputers. △ Less

Submitted 9 January, 2026; originally announced January 2026.

Comments: 5 pages, 4 figures

Journal ref: Architecture Letters, vol., no. 01, pp. 1-4, PrePrints 5555

The Hidden Cost of Straight Lines: Quantifying Misallocation Risk in Voronoi-based Service Area Models

Authors: JA Torrecilla Pinero, JM Ceballos Martínez, A Cuartero Sáez, P Plaza Caballero, A Cruces López

Abstract: Voronoi tessellations are standard in spatial planning for assigning service areas based on Euclidean proximity, underpinning regulatory frameworks like the proximity principle in waste management. However, in regions with complex topography, Euclidean distance poorly approximates functional accessibility, causing misallocations that undermine efficiency and equity. This paper develops a probabili… ▽ More Voronoi tessellations are standard in spatial planning for assigning service areas based on Euclidean proximity, underpinning regulatory frameworks like the proximity principle in waste management. However, in regions with complex topography, Euclidean distance poorly approximates functional accessibility, causing misallocations that undermine efficiency and equity. This paper develops a probabilistic framework to quantify misallocation risk by modeling travel distances as random scaling of Euclidean distances and deriving incorrect assignment probability as a function of local Voronoi geometry. Using plant-municipality observations (n=383) in Extremadura, Spain (41,635 km2), we demonstrate that the Log-Normal distribution provides best relative fit among alternatives (K-S statistic=0.110). Validation reveals 15.4% of municipalities are misallocated, consistent with the theoretical prediction interval (52-65 municipalities at 95% confidence). Our framework achieves 95% agreement with complex spatial models at O(n) complexity. Poor absolute fit of global distributions (p-values<0.01) reflects diverse topography (elevation 200-2,400m), motivating spatial stratification. Sensitivity analysis validates the fitted dispersion parameter (s=0.093) for predicting observed misallocation. We provide a calibration protocol requiring only 30-100 pilot samples per zone, enabling rapid risk assessment without full network analysis. This establishes the first probabilistic framework for Voronoi misallocation risk with practical guidelines emphasizing spatial heterogeneity and context-dependent calibration. △ Less

Submitted 1 December, 2025; originally announced December 2025.

Comments: 20 pages, 18 figures, reproducibility repository included

Deadlock-free routing for Full-mesh networks without using Virtual Channels

Authors: Alejandro Cano, Cristóbal Camarero, Carmen Martínez, Ramón Beivide

Abstract: High-radix, low-diameter networks like HyperX and Dragonfly use a Full-mesh core, and rely on multiple virtual channels (VCs) to avoid packet deadlocks in adaptive routing. However, VCs introduce significant overhead in the switch in terms of area, power, and design complexity, limiting the switch scalability. This paper starts by revisiting VC-less routing through link ordering schemes in Full-me… ▽ More High-radix, low-diameter networks like HyperX and Dragonfly use a Full-mesh core, and rely on multiple virtual channels (VCs) to avoid packet deadlocks in adaptive routing. However, VCs introduce significant overhead in the switch in terms of area, power, and design complexity, limiting the switch scalability. This paper starts by revisiting VC-less routing through link ordering schemes in Full-mesh networks, which offer implementation simplicity but suffer from performance degradation under adversarial traffic. Thus, to overcome these challenges, we propose TERA (Topology-Embedded Routing Algorithm), a novel routing algorithm which employs an embedded physical subnetwork to provide deadlock-free non-minimal paths without using VCs. In a Full-mesh network, TERA outperforms link ordering routing algorithms by 80% when dealing with adversarial traffic, and up to 100% in application kernels. Furthermore, compared to other VC-based approaches, it reduces buffer requirements by 50%, while maintaining comparable latency and throughput. Lastly, early results from a 2D-HyperX evaluation show that TERA outperforms state-of-the-art algorithms that use the same number of VCs, achieving performance improvements of up to 32%. △ Less

Submitted 16 October, 2025; originally announced October 2025.

Space Robotics Bench: Robot Learning Beyond Earth

Authors: Andrej Orsula, Matthieu Geist, Miguel Olivares-Mendez, Carol Martinez

Abstract: The growing ambition for space exploration demands robust autonomous systems that can operate in unstructured environments under extreme extraterrestrial conditions. The adoption of robot learning in this domain is severely hindered by the prohibitive cost of technology demonstrations and the limited availability of data. To bridge this gap, we introduce the Space Robotics Bench, an open-source si… ▽ More The growing ambition for space exploration demands robust autonomous systems that can operate in unstructured environments under extreme extraterrestrial conditions. The adoption of robot learning in this domain is severely hindered by the prohibitive cost of technology demonstrations and the limited availability of data. To bridge this gap, we introduce the Space Robotics Bench, an open-source simulation framework for robot learning in space. It offers a modular architecture that integrates on-demand procedural generation with massively parallel simulation environments to support the creation of vast and diverse training distributions for learning-based agents. To ground research and enable direct comparison, the framework includes a comprehensive suite of benchmark tasks that span a wide range of mission-relevant scenarios. We establish performance baselines using standard reinforcement learning algorithms and present a series of experimental case studies that investigate key challenges in generalization, end-to-end learning, adaptive control, and sim-to-real transfer. Our results reveal insights into the limitations of current methods and demonstrate the utility of the framework in producing policies capable of real-world operation. These contributions establish the Space Robotics Bench as a valuable resource for developing, benchmarking, and deploying the robust autonomous systems required for the final frontier. △ Less

Submitted 27 September, 2025; originally announced September 2025.

Comments: The source code is available at https://github.com/AndrejOrsula/space_robotics_bench

Learning Tool-Aware Adaptive Compliant Control for Autonomous Regolith Excavation

Authors: Andrej Orsula, Matthieu Geist, Miguel Olivares-Mendez, Carol Martinez

Abstract: Autonomous regolith excavation is a cornerstone of in-situ resource utilization for a sustained human presence beyond Earth. However, this task is fundamentally hindered by the complex interaction dynamics of granular media and the operational need for robots to use diverse tools. To address these challenges, this work introduces a framework where a model-based reinforcement learning agent learns… ▽ More Autonomous regolith excavation is a cornerstone of in-situ resource utilization for a sustained human presence beyond Earth. However, this task is fundamentally hindered by the complex interaction dynamics of granular media and the operational need for robots to use diverse tools. To address these challenges, this work introduces a framework where a model-based reinforcement learning agent learns within a parallelized simulation. This environment leverages high-fidelity particle physics and procedural generation to create a vast distribution of both lunar terrains and excavation tool geometries. To master this diversity, the agent learns an adaptive interaction strategy by dynamically modulating its own stiffness and damping at each control step through operational space control. Our experiments demonstrate that training with a procedural distribution of tools is critical for generalization and enables the development of sophisticated tool-aware behavior. Furthermore, we show that augmenting the agent with visual feedback significantly improves task success. These results represent a validated methodology for developing the robust and versatile autonomous systems required for the foundational tasks of future space missions. △ Less

Submitted 5 September, 2025; originally announced September 2025.

Comments: The source code is available at https://github.com/AndrejOrsula/space_robotics_bench

Sim2Dust: Mastering Dynamic Waypoint Tracking on Granular Media

Authors: Andrej Orsula, Matthieu Geist, Miguel Olivares-Mendez, Carol Martinez

Abstract: Reliable autonomous navigation across the unstructured terrains of distant planetary surfaces is a critical enabler for future space exploration. However, the deployment of learning-based controllers is hindered by the inherent sim-to-real gap, particularly for the complex dynamics of wheel interactions with granular media. This work presents a complete sim-to-real framework for developing and val… ▽ More Reliable autonomous navigation across the unstructured terrains of distant planetary surfaces is a critical enabler for future space exploration. However, the deployment of learning-based controllers is hindered by the inherent sim-to-real gap, particularly for the complex dynamics of wheel interactions with granular media. This work presents a complete sim-to-real framework for developing and validating robust control policies for dynamic waypoint tracking on such challenging surfaces. We leverage massively parallel simulation to train reinforcement learning agents across a vast distribution of procedurally generated environments with randomized physics. These policies are then transferred zero-shot to a physical wheeled rover operating in a lunar-analogue facility. Our experiments systematically compare multiple reinforcement learning algorithms and action smoothing filters to identify the most effective combinations for real-world deployment. Crucially, we provide strong empirical evidence that agents trained with procedural diversity achieve superior zero-shot performance compared to those trained on static scenarios. We also analyze the trade-offs of fine-tuning with high-fidelity particle physics, which offers minor gains in low-speed precision at a significant computational cost. Together, these contributions establish a validated workflow for creating reliable learning-based navigation systems, marking a substantial step towards deploying autonomous robots in the final frontier. △ Less

Submitted 20 October, 2025; v1 submitted 15 August, 2025; originally announced August 2025.

Comments: Accepted for publication at the 2025 International Conference on Space Robotics (iSpaRo) | The source code is available at https://github.com/AndrejOrsula/space_robotics_bench

Distinguishing Target and Non-Target Fixations with EEG and Eye Tracking in Realistic Visual Scenes

Authors: Mansi Sharma, Camilo Andrés Martínez Martínez, Benedikt Emanuel Wirth, Antonio Krüger, Philipp Müller

Abstract: Distinguishing target from non-target fixations during visual search is a fundamental building block to understand users' intended actions and to build effective assistance systems. While prior research indicated the feasibility of classifying target vs. non-target fixations based on eye tracking and electroencephalography (EEG) data, these studies were conducted with explicitly instructed search… ▽ More Distinguishing target from non-target fixations during visual search is a fundamental building block to understand users' intended actions and to build effective assistance systems. While prior research indicated the feasibility of classifying target vs. non-target fixations based on eye tracking and electroencephalography (EEG) data, these studies were conducted with explicitly instructed search trajectories, abstract visual stimuli, and disregarded any scene context. This is in stark contrast with the fact that human visual search is largely driven by scene characteristics and raises questions regarding generalizability to more realistic scenarios. To close this gap, we, for the first time, investigate the classification of target vs. non-target fixations during free visual search in realistic scenes. In particular, we conducted a 36-participants user study using a large variety of 140 realistic visual search scenes in two highly relevant application scenarios: searching for icons on desktop backgrounds and finding tools in a cluttered workshop. Our approach based on gaze and EEG features outperforms the previous state-of-the-art approach based on a combination of fixation duration and saccade-related potentials. We perform extensive evaluations to assess the generalizability of our approach across scene types. Our approach significantly advances the ability to distinguish between target and non-target fixations in realistic scenarios, achieving 83.6% accuracy in cross-user evaluations. This substantially outperforms previous methods based on saccade-related potentials, which reached only 56.9% accuracy. △ Less

Submitted 3 August, 2025; originally announced August 2025.

Journal ref: ACM ICMI 2024

Benchmarking Waitlist Mortality Prediction in Heart Transplantation Through Time-to-Event Modeling using New Longitudinal UNOS Dataset

Authors: Yingtao Luo, Reza Skandari, Carlos Martinez, Arman Kilic, Rema Padman

Abstract: Decisions about managing patients on the heart transplant waitlist are currently made by committees of doctors who consider multiple factors, but the process remains largely ad-hoc. With the growing volume of longitudinal patient, donor, and organ data collected by the United Network for Organ Sharing (UNOS) since 2018, there is increasing interest in analytical approaches to support clinical deci… ▽ More Decisions about managing patients on the heart transplant waitlist are currently made by committees of doctors who consider multiple factors, but the process remains largely ad-hoc. With the growing volume of longitudinal patient, donor, and organ data collected by the United Network for Organ Sharing (UNOS) since 2018, there is increasing interest in analytical approaches to support clinical decision-making at the time of organ availability. In this study, we benchmark machine learning models that leverage longitudinal waitlist history data for time-dependent, time-to-event modeling of waitlist mortality. We train on 23,807 patient records with 77 variables and evaluate both survival prediction and discrimination at a 1-year horizon. Our best model achieves a C-Index of 0.94 and AUROC of 0.89, significantly outperforming previous models. Key predictors align with known risk factors while also revealing novel associations. Our findings can support urgency assessment and policy refinement in heart transplant decision making. △ Less

Submitted 9 July, 2025; originally announced July 2025.

Comments: To appear in the Proceedings of AMIA Annual Symposium 2025

Large Language Models for Automating Clinical Data Standardization: HL7 FHIR Use Case

Authors: Alvaro Riquelme, Pedro Costa, Catalina Martinez

Abstract: For years, semantic interoperability standards have sought to streamline the exchange of clinical data, yet their deployment remains time-consuming, resource-intensive, and technically challenging. To address this, we introduce a semi-automated approach that leverages large language models specifically GPT-4o and Llama 3.2 405b to convert structured clinical datasets into HL7 FHIR format while ass… ▽ More For years, semantic interoperability standards have sought to streamline the exchange of clinical data, yet their deployment remains time-consuming, resource-intensive, and technically challenging. To address this, we introduce a semi-automated approach that leverages large language models specifically GPT-4o and Llama 3.2 405b to convert structured clinical datasets into HL7 FHIR format while assessing accuracy, reliability, and security. Applying our method to the MIMIC-IV database, we combined embedding techniques, clustering algorithms, and semantic retrieval to craft prompts that guide the models in mapping each tabular field to its corresponding FHIR resource. In an initial benchmark, resource identification achieved a perfect F1-score, with GPT-4o outperforming Llama 3.2 thanks to the inclusion of FHIR resource schemas within the prompt. Under real-world conditions, accuracy dipped slightly to 94 %, but refinements to the prompting strategy restored robust mappings. Error analysis revealed occasional hallucinations of non-existent attributes and mismatches in granularity, which more detailed prompts can mitigate. Overall, our study demonstrates the feasibility of context-aware, LLM-driven transformation of clinical data into HL7 FHIR, laying the groundwork for semi-automated interoperability workflows. Future work will focus on fine-tuning models with specialized medical corpora, extending support to additional standards such as HL7 CDA and OMOP, and developing an interactive interface to enable expert validation and iterative refinement. △ Less

Submitted 3 July, 2025; originally announced July 2025.

Comments: 10 pages, 2 figures

Identity and Access Management for the Computing Continuum

Authors: Chalima Dimitra Nassar Kyriakidou, Athanasia Maria Papathanasiou, Vasilios A. Siris, Nikos Fotiou, George C. Polyzos, Eduardo Cánovas Martínez, Antonio Skarmeta

Abstract: The computing continuum introduces new challenges for access control due to its dynamic, distributed, and heterogeneous nature. In this paper, we propose a Zero-Trust (ZT) access control solution that leverages decentralized identification and authentication mechanisms based on Decentralized Identifiers (DIDs) and Verifiable Credentials (VCs). Additionally, we employ Relationship-Based Access Cont… ▽ More The computing continuum introduces new challenges for access control due to its dynamic, distributed, and heterogeneous nature. In this paper, we propose a Zero-Trust (ZT) access control solution that leverages decentralized identification and authentication mechanisms based on Decentralized Identifiers (DIDs) and Verifiable Credentials (VCs). Additionally, we employ Relationship-Based Access Control (ReBAC) to define policies that capture the evolving trust relationships inherent in the continuum. Through a proof-of-concept implementation, we demonstrate the feasibility and efficiency of our solution, highlighting its potential to enhance security and trust in decentralized environments. △ Less

Submitted 11 June, 2025; originally announced June 2025.

Comments: Proceedings of the 2nd International Workshop on MetaOS for the Cloud-Edge-IoT Continuum, pp 33-39. 2025

Learning from Stochastic Teacher Representations Using Student-Guided Knowledge Distillation

Authors: Muhammad Haseeb Aslam, Clara Martinez, Marco Pedersoli, Alessandro Koerich, Ali Etemad, Eric Granger

Abstract: Advances in self-distillation have shown that when knowledge is distilled from a teacher to a student using the same deep learning (DL) architecture, the student performance can surpass the teacher particularly when the network is overparameterized and the teacher is trained with early stopping. Alternatively, ensemble learning also improves performance, although training, storing, and deploying m… ▽ More Advances in self-distillation have shown that when knowledge is distilled from a teacher to a student using the same deep learning (DL) architecture, the student performance can surpass the teacher particularly when the network is overparameterized and the teacher is trained with early stopping. Alternatively, ensemble learning also improves performance, although training, storing, and deploying multiple models becomes impractical as the number of models grows. Even distilling an ensemble to a single student model or weight averaging methods first requires training of multiple teacher models and does not fully leverage the inherent stochasticity for generating and distilling diversity in DL models. These constraints are particularly prohibitive in resource-constrained or latency-sensitive applications such as wearable devices. This paper proposes to train only one model and generate multiple diverse teacher representations using distillation-time dropout. However, generating these representations stochastically leads to noisy representations that are misaligned with the learned task. To overcome this problem, a novel stochastic self-distillation (SSD) training strategy is introduced for filtering and weighting teacher representation to distill from task-relevant representations only, using student-guided knowledge distillation (SGKD). The student representation at each distillation step is used as authority to guide the distillation process. Experimental results on real-world affective computing, wearable/biosignal datasets from the UCR Archive, the HAR dataset, and image classification datasets show that the proposed SSD method can outperform state-of-the-art methods without increasing the model size at both training and testing time, and incurs negligible computational complexity compared to state-of-the-art ensemble learning and weight averaging methods. △ Less

Submitted 23 June, 2025; v1 submitted 19 April, 2025; originally announced April 2025.

EMERALD: Evidence Management for Continuous Certification as a Service in the Cloud

Authors: Christian Banse, Björn Fanta, Juncal Alonso, Cristina Martinez

Abstract: The conspicuous lack of cloud-specific security certifications, in addition to the existing market fragmentation, hinder transparency and accountability in the provision and usage of European cloud services. Both issues ultimately reflect on the level of customers' trustworthiness and adoption of cloud services. The upcoming demand for continuous certification has not yet been definitively address… ▽ More The conspicuous lack of cloud-specific security certifications, in addition to the existing market fragmentation, hinder transparency and accountability in the provision and usage of European cloud services. Both issues ultimately reflect on the level of customers' trustworthiness and adoption of cloud services. The upcoming demand for continuous certification has not yet been definitively addressed and it remains unclear how the level 'high' of the European Cybersecurity Certification Scheme for Cloud Services (EUCS) shall be technologically achieved. The introduction of AI in cloud services is raising the complexity of certification even further. This paper presents the EMERALD Certification-as-a-Service (CaaS) concept for continuous certification of harmonized cybersecurity schemes, like the EUCS. EMERALD CaaS aims to provide agile and lean re-certification to consumers that adhere to a defined level of security and trust in a uniform way across heterogeneous environments consisting of combinations of different resources (Cloud, Edge, IoT). Initial findings suggest that EMERALD will significantly contribute to continuous certification, boosting providers and users of cloud services to maintain regulatory compliance towards the latest and upcoming security schemes. △ Less

Submitted 11 February, 2025; originally announced February 2025.

Comments: Accepted for publication at CLOSER 2025

Hybrid Decision Making for Scalable Multi-Agent Navigation: Integrating Semantic Maps, Discrete Coordination, and Model Predictive Control

Authors: Koen de Vos, Elena Torta, Herman Bruyninckx, Cesar Lopez Martinez, Rene van de Molengraft

Abstract: This paper presents a framework for multi-agent navigation in structured but dynamic environments, integrating three key components: a shared semantic map encoding metric and semantic environmental knowledge, a claim policy for coordinating access to areas within the environment, and a Model Predictive Controller for generating motion trajectories that respect environmental and coordination constr… ▽ More This paper presents a framework for multi-agent navigation in structured but dynamic environments, integrating three key components: a shared semantic map encoding metric and semantic environmental knowledge, a claim policy for coordinating access to areas within the environment, and a Model Predictive Controller for generating motion trajectories that respect environmental and coordination constraints. The main advantages of this approach include: (i) enforcing area occupancy constraints derived from specific task requirements; (ii) enhancing computational scalability by eliminating the need for collision avoidance constraints between robotic agents; and (iii) the ability to anticipate and avoid deadlocks between agents. The paper includes both simulations and physical experiments demonstrating the framework's effectiveness in various representative scenarios. △ Less

Submitted 16 October, 2024; originally announced October 2024.

Human Stone Toolmaking Action Grammar (HSTAG): A Challenging Benchmark for Fine-grained Motor Behavior Recognition

Authors: Cheng Liu, Xuyang Yan, Zekun Zhang, Cheng Ding, Tianhao Zhao, Shaya Jannati, Cynthia Martinez, Dietrich Stout

Abstract: Action recognition has witnessed the development of a growing number of novel algorithms and datasets in the past decade. However, the majority of public benchmarks were constructed around activities of daily living and annotated at a rather coarse-grained level, which lacks diversity in domain-specific datasets, especially for rarely seen domains. In this paper, we introduced Human Stone Toolmaki… ▽ More Action recognition has witnessed the development of a growing number of novel algorithms and datasets in the past decade. However, the majority of public benchmarks were constructed around activities of daily living and annotated at a rather coarse-grained level, which lacks diversity in domain-specific datasets, especially for rarely seen domains. In this paper, we introduced Human Stone Toolmaking Action Grammar (HSTAG), a meticulously annotated video dataset showcasing previously undocumented stone toolmaking behaviors, which can be used for investigating the applications of advanced artificial intelligence techniques in understanding a rapid succession of complex interactions between two hand-held objects. HSTAG consists of 18,739 video clips that record 4.5 hours of experts' activities in stone toolmaking. Its unique features include (i) brief action durations and frequent transitions, mirroring the rapid changes inherent in many motor behaviors; (ii) multiple angles of view and switches among multiple tools, increasing intra-class variability; (iii) unbalanced class distributions and high similarity among different action sequences, adding difficulty in capturing distinct patterns for each action. Several mainstream action recognition models are used to conduct experimental analysis, which showcases the challenges and uniqueness of HSTAG https://nyu.databrary.org/volume/1697. △ Less

Submitted 10 October, 2024; originally announced October 2024.

Comments: 8 pages, 4 figures, accepted by the 11th IEEE International Conference on Data Science and Advanced Analytics (DSAA)

Graph Convolutional Neural Networks as Surrogate Models for Climate Simulation

Authors: Kevin Potter, Carianne Martinez, Reina Pradhan, Samantha Brozak, Steven Sleder, Lauren Wheeler

Abstract: Many climate processes are characterized using large systems of nonlinear differential equations; this, along with the immense amount of data required to parameterize complex interactions, means that Earth-System Model (ESM) simulations may take weeks to run on large clusters. Uncertainty quantification may require thousands of runs, making ESM simulations impractical for preliminary assessment. A… ▽ More Many climate processes are characterized using large systems of nonlinear differential equations; this, along with the immense amount of data required to parameterize complex interactions, means that Earth-System Model (ESM) simulations may take weeks to run on large clusters. Uncertainty quantification may require thousands of runs, making ESM simulations impractical for preliminary assessment. Alternatives may include simplifying the processes in the model, but recent efforts have focused on using machine learning to complement these models or even act as full surrogates. \textit{We leverage machine learning, specifically fully-connected neural networks (FCNNs) and graph convolutional neural networks (GCNNs), to enable rapid simulation and uncertainty quantification in order to inform more extensive ESM simulations.} Our surrogate simulated 80 years in approximately 310 seconds on a single A100 GPU, compared to weeks for the ESM model while having mean temperature errors below $0.1^{\circ}C$ and maximum errors below $2^{\circ}C$. △ Less

Submitted 19 September, 2024; originally announced September 2024.

Comments: 10 pages, 8 figures

Visual Servoing for Robotic On-Orbit Servicing: A Survey

Authors: Lina María Amaya-Mejía, Mohamed Ghita, Jan Dentler, Miguel Olivares-Mendez, Carol Martinez

Abstract: On-orbit servicing (OOS) activities will power the next big step for sustainable exploration and commercialization of space. Developing robotic capabilities for autonomous OOS operations is a priority for the space industry. Visual Servoing (VS) enables robots to achieve the precise manoeuvres needed for critical OOS missions by utilizing visual information for motion control. This article present… ▽ More On-orbit servicing (OOS) activities will power the next big step for sustainable exploration and commercialization of space. Developing robotic capabilities for autonomous OOS operations is a priority for the space industry. Visual Servoing (VS) enables robots to achieve the precise manoeuvres needed for critical OOS missions by utilizing visual information for motion control. This article presents an overview of existing VS approaches for autonomous OOS operations with space manipulator systems (SMS). We divide the approaches according to their contribution to the typical phases of a robotic OOS mission: a) Recognition, b) Approach, and c) Contact. We also present a discussion on the reviewed VS approaches, identifying current trends. Finally, we highlight the challenges and areas for future research on VS techniques for robotic OOS. △ Less

Submitted 3 September, 2024; originally announced September 2024.

Comments: Accepted for publication at the 2024 International Conference on Space Robotics (iSpaRo)

Object-centric Reconstruction and Tracking of Dynamic Unknown Objects using 3D Gaussian Splatting

Authors: Kuldeep R Barad, Antoine Richard, Jan Dentler, Miguel Olivares-Mendez, Carol Martinez

Abstract: Generalizable perception is one of the pillars of high-level autonomy in space robotics. Estimating the structure and motion of unknown objects in dynamic environments is fundamental for such autonomous systems. Traditionally, the solutions have relied on prior knowledge of target objects, multiple disparate representations, or low-fidelity outputs unsuitable for robotic operations. This work prop… ▽ More Generalizable perception is one of the pillars of high-level autonomy in space robotics. Estimating the structure and motion of unknown objects in dynamic environments is fundamental for such autonomous systems. Traditionally, the solutions have relied on prior knowledge of target objects, multiple disparate representations, or low-fidelity outputs unsuitable for robotic operations. This work proposes a novel approach to incrementally reconstruct and track a dynamic unknown object using a unified representation -- a set of 3D Gaussian blobs that describe its geometry and appearance. The differentiable 3D Gaussian Splatting framework is adapted to a dynamic object-centric setting. The input to the pipeline is a sequential set of RGB-D images. 3D reconstruction and 6-DoF pose tracking tasks are tackled using first-order gradient-based optimization. The formulation is simple, requires no pre-training, assumes no prior knowledge of the object or its motion, and is suitable for online applications. The proposed approach is validated on a dataset of 10 unknown spacecraft of diverse geometry and texture under arbitrary relative motion. The experiments demonstrate successful 3D reconstruction and accurate 6-DoF tracking of the target object in proximity operations over a short to medium duration. The causes of tracking drift are discussed and potential solutions are outlined. △ Less

Submitted 18 September, 2024; v1 submitted 30 May, 2024; originally announced May 2024.

Comments: Accepted at IEEE International Conference on Space Robotics 2024

Journal ref: 2024 International Conference on Space Robotics (iSpaRo), Luxembourg, 2024, pp. 202-209

Leveraging Procedural Generation for Learning Autonomous Peg-in-Hole Assembly in Space

Authors: Andrej Orsula, Matthieu Geist, Miguel Olivares-Mendez, Carol Martinez

Abstract: The ability to autonomously assemble structures is crucial for the development of future space infrastructure. However, the unpredictable conditions of space pose significant challenges for robotic systems, necessitating the development of advanced learning techniques to enable autonomous assembly. In this study, we present a novel approach for learning autonomous peg-in-hole assembly in the conte… ▽ More The ability to autonomously assemble structures is crucial for the development of future space infrastructure. However, the unpredictable conditions of space pose significant challenges for robotic systems, necessitating the development of advanced learning techniques to enable autonomous assembly. In this study, we present a novel approach for learning autonomous peg-in-hole assembly in the context of space robotics. Our focus is on enhancing the generalization and adaptability of autonomous systems through deep reinforcement learning. By integrating procedural generation and domain randomization, we train agents in a highly parallelized simulation environment across a spectrum of diverse scenarios with the aim of acquiring a robust policy. The proposed approach is evaluated using three distinct reinforcement learning algorithms to investigate the trade-offs among various paradigms. We demonstrate the adaptability of our agents to novel scenarios and assembly sequences while emphasizing the potential of leveraging advanced simulation techniques for robot learning in space. Our findings set the stage for future advancements in intelligent robotic systems capable of supporting ambitious space missions and infrastructure development beyond Earth. △ Less

Submitted 2 May, 2024; originally announced May 2024.

Comments: Accepted for publication at the 2024 International Conference on Space Robotics (iSpaRo) | The source code is available at https://github.com/AndrejOrsula/drl_omni_peg

Journal ref: 2024 International Conference on Space Robotics (iSpaRo), pp. 357-364

Achieving High-Performance Fault-Tolerant Routing in HyperX Interconnection Networks

Authors: Cristóbal Camarero, Alejandro Cano, Carmen Martínez, Ramón Beivide

Abstract: Interconnection networks are key actors that condition the performance of current large datacenter and supercomputer systems. Both topology and routing are critical aspects that must be carefully considered for a competitive system network design. Moreover, when daily failures are expected, this tandem should exhibit resilience and robustness. Low-diameter networks, including HyperX, are cheaper t… ▽ More Interconnection networks are key actors that condition the performance of current large datacenter and supercomputer systems. Both topology and routing are critical aspects that must be carefully considered for a competitive system network design. Moreover, when daily failures are expected, this tandem should exhibit resilience and robustness. Low-diameter networks, including HyperX, are cheaper than typical Fat Trees. But, to be really competitive, they have to employ evolved routing algorithms to both balance traffic and tolerate failures. In this paper, SurePath, an efficient fault-tolerant routing mechanism for HyperX topology is introduced and evaluated. SurePath leverages routes provided by standard routing algorithms and a deadlock avoidance mechanism based on an Up/Down escape subnetwork. This mechanism not only prevents deadlock but also allows for a fault-tolerant solution for these networks. SurePath is thoroughly evaluated in the paper under different traffic patterns, showing no performance degradation under extremely faulty scenarios. △ Less

Submitted 5 April, 2024; originally announced April 2024.

Using Game Design to Inform a Plastics Treaty: Fostering Collaboration between Science, Machine Learning, and Policymaking

Authors: A Samuel Pottinger, Nivedita Biyani, Roland Geyer, Douglas J McCauley, Magali de Bruyn, Molly R Morse, Neil Nathan, Kevin Koy, Ciera Martinez

Abstract: Introduction: This multi-disciplinary case study details how an interactive decision support tool leverages game design to inform an international plastic pollution treaty. Design: Seeking to make our scientific findings more usable within the policy process, our interactive software supports manipulation of a mathematical model using techniques borrowed from games. These "ludic" approaches aim… ▽ More Introduction: This multi-disciplinary case study details how an interactive decision support tool leverages game design to inform an international plastic pollution treaty. Design: Seeking to make our scientific findings more usable within the policy process, our interactive software supports manipulation of a mathematical model using techniques borrowed from games. These "ludic" approaches aim to enable user agency to find custom policy solutions, invite deep engagement with scientific results, serve audiences of diverse expertise, and accelerate scientific process to keep pace with intergovernmental negotiations. Implementation: Built in JavaScript and D3 with user-modifiable logic via an ANTLR domain specific language, this browser-based application offers adaptability and explorability for our machine learning results with privacy preserving architecture and offline capability. Demonstration: Policymakers and the supporting community engaged with this public simulation tool across multiple treaty-related events, investigating plastic waste outcomes under diverse and sometimes unexpected policy scenarios. Conclusion: Contextualizing our open source software within a broader lineage of digital media research, we reflect on this interactive modeling platform, considering how game design approaches may help facilitate collaboration at the science / policy nexus. Materials: Available on the public Internet, we host this browser-based decision support tool at global-plastics-tool.org, work also archived at zenodo.org/records/12615011 in a Docker container. △ Less

Submitted 2 December, 2025; v1 submitted 18 December, 2023; originally announced December 2023.

Comments: 17 pages, 3 figures, latex generated from markdown via Pandoc (https://pandoc.org/) for Arxiv,

GraspLDM: Generative 6-DoF Grasp Synthesis using Latent Diffusion Models

Authors: Kuldeep R Barad, Andrej Orsula, Antoine Richard, Jan Dentler, Miguel Olivares-Mendez, Carol Martinez

Abstract: Vision-based grasping of unknown objects in unstructured environments is a key challenge for autonomous robotic manipulation. A practical grasp synthesis system is required to generate a diverse set of 6-DoF grasps from which a task-relevant grasp can be executed. Although generative models are suitable for learning such complex data distributions, existing models have limitations in grasp quality… ▽ More Vision-based grasping of unknown objects in unstructured environments is a key challenge for autonomous robotic manipulation. A practical grasp synthesis system is required to generate a diverse set of 6-DoF grasps from which a task-relevant grasp can be executed. Although generative models are suitable for learning such complex data distributions, existing models have limitations in grasp quality, long training times, and a lack of flexibility for task-specific generation. In this work, we present GraspLDM, a modular generative framework for 6-DoF grasp synthesis that uses diffusion models as priors in the latent space of a VAE. GraspLDM learns a generative model of object-centric $SE(3)$ grasp poses conditioned on point clouds. GraspLDM architecture enables us to train task-specific models efficiently by only re-training a small denoising network in the low-dimensional latent space, as opposed to existing models that need expensive re-training. Our framework provides robust and scalable models on both full and partial point clouds. GraspLDM models trained with simulation data transfer well to the real world without any further fine-tuning. Our models provide an 80% success rate for 80 grasp attempts of diverse test objects across two real-world robotic setups. We make our implementation available at https://github.com/kuldeepbrd1/graspldm . △ Less

Submitted 22 November, 2024; v1 submitted 18 December, 2023; originally announced December 2023.

Journal ref: IEEE Access, vol. 12, pp. 164621-164633, 2024

Agile, User-Centered Design and Quality in Software Processes for Mobile Application Development Teaching

Authors: Manuel Ignacio Castillo López, Ana Libia Eslava Cervantes, Gustavo de la Cruz Martínez, Jorge Luis Ortega Arjona

Abstract: Agile methods in undergraduate courses have been explored in an effort to close the gap between industry and professional profiles. We have structured an Android application development course based on a tailored user-centered Agile process for development of educational digital tools. This process is based on Scrum and Extreme Programming in combination with User Experience (UX) approaches. The c… ▽ More Agile methods in undergraduate courses have been explored in an effort to close the gap between industry and professional profiles. We have structured an Android application development course based on a tailored user-centered Agile process for development of educational digital tools. This process is based on Scrum and Extreme Programming in combination with User Experience (UX) approaches. The course is executed in two phases: the first half of the semester presents theory on Agile and mobile applications development, the latter half is managed as a workshop where students develop for an actual client. The introduction of UX and user-centered design exploiting the close relationship with stakeholders expected from Agile processes allows for different quality features development. Since 2019 two of the projects have been extended and one project has been developed with the described process and course alumni. Students and stakeholders have found value in the generated products and process. △ Less

Submitted 25 September, 2023; originally announced November 2023.

Comments: 17 pages, 6 figures. arXiv admin note: substantial text overlap with arXiv:2308.07494

Journal ref: International Journal of Software Engineering & Applications (2023), vol. 15, no. 5, pages 1-17

Automatic Configuration of Multi-Agent Model Predictive Controllers based on Semantic Graph World Models

Authors: K. de Vos, E. Torta, H. Bruyninckx, C. A. Lopez Martinez, M. J. G. van de Molengraft

Abstract: We propose a shared semantic map architecture to construct and configure Model Predictive Controllers (MPC) dynamically, that solve navigation problems for multiple robotic agents sharing parts of the same environment. The navigation task is represented as a sequence of semantically labeled areas in the map, that must be traversed sequentially, i.e. a route. Each semantic label represents one or m… ▽ More We propose a shared semantic map architecture to construct and configure Model Predictive Controllers (MPC) dynamically, that solve navigation problems for multiple robotic agents sharing parts of the same environment. The navigation task is represented as a sequence of semantically labeled areas in the map, that must be traversed sequentially, i.e. a route. Each semantic label represents one or more constraints on the robots' motion behaviour in that area. The advantages of this approach are: (i) an MPC-based motion controller in each individual robot can be (re-)configured, at runtime, with the locally and temporally relevant parameters; (ii) the application can influence, also at runtime, the navigation behaviour of the robots, just by adapting the semantic labels; and (iii) the robots can reason about their need for coordination, through analyzing over which horizon in time and space their routes overlap. The paper provides simulations of various representative situations, showing that the approach of runtime configuration of the MPC drastically decreases computation time, while retaining task execution performance similar to an approach in which each robot always includes all other robots in its MPC computations. △ Less

Submitted 2 November, 2023; originally announced November 2023.

Causal disentanglement of multimodal data

Authors: Elise Walker, Jonas A. Actor, Carianne Martinez, Nathaniel Trask

Abstract: Causal representation learning algorithms discover lower-dimensional representations of data that admit a decipherable interpretation of cause and effect; as achieving such interpretable representations is challenging, many causal learning algorithms utilize elements indicating prior information, such as (linear) structural causal models, interventional data, or weak supervision. Unfortunately, in… ▽ More Causal representation learning algorithms discover lower-dimensional representations of data that admit a decipherable interpretation of cause and effect; as achieving such interpretable representations is challenging, many causal learning algorithms utilize elements indicating prior information, such as (linear) structural causal models, interventional data, or weak supervision. Unfortunately, in exploratory causal representation learning, such elements and prior information may not be available or warranted. Alternatively, scientific datasets often have multiple modalities or physics-based constraints, and the use of such scientific, multimodal data has been shown to improve disentanglement in fully unsupervised settings. Consequently, we introduce a causal representation learning algorithm (causalPIMA) that can use multimodal data and known physics to discover important features with causal relationships. Our innovative algorithm utilizes a new differentiable parametrization to learn a directed acyclic graph (DAG) together with a latent space of a variational autoencoder in an end-to-end differentiable framework via a single, tractable evidence lower bound loss function. We place a Gaussian mixture prior on the latent space and identify each of the mixtures with an outcome of the DAG nodes; this novel identification enables feature discovery with causal relationships. Tested against a synthetic and a scientific dataset, our results demonstrate the capability of learning an interpretable causal structure while simultaneously discovering key features in a fully unsupervised setting. △ Less

Submitted 8 November, 2023; v1 submitted 27 October, 2023; originally announced October 2023.

MSC Class: 68T07

Mapping Election Polarization and Competitiveness using Election Results

Authors: Carlos Navarrete, Mariana Macedo, Viktor Stojkoski, Marcela Parada-Contzen, Christopher A Martínez

Abstract: The simplified hypothesis that an election is polarized as an explanation of recent electoral outcomes worldwide is centered on perceptions of voting patterns rather than ideological data from the electorate. While the literature focuses on measuring polarization using ideological-like data from electoral studies-which are limited to economically advantageous countries and are representative mostl… ▽ More The simplified hypothesis that an election is polarized as an explanation of recent electoral outcomes worldwide is centered on perceptions of voting patterns rather than ideological data from the electorate. While the literature focuses on measuring polarization using ideological-like data from electoral studies-which are limited to economically advantageous countries and are representative mostly to national scales-we argue that, in fact, voting patterns can lead to mapping effective proxies of citizen divisions on election day. This paper perspectives two complementary concepts, Election Polarization (EP) and Election Competitiveness (EC), as a means to understand voting patterns on Election Day. We present an agnostic approach that relies solely on election data and validate it using synthetic and real-world election data across 13 countries in the Eurozone, North America, Latin America, and New Zealand. Overall, we find that we can label and distinguish expectations of polarized and competitive elections in these countries, and we report that EP positively correlates with a metric of political polarization in the U.S., unlocking opportunities for studies of polarization at the regional level and for lower/middle-income countries where electoral studies are available, but surveys are limited. △ Less

Submitted 27 July, 2024; v1 submitted 16 August, 2023; originally announced August 2023.

Applying User Experience and User-Centered Design Software Processes in Undergraduate Mobile Application Development Teaching

Authors: Manuel Ignacio Castillo López, Ana Libia Eslava Cervantes, Gustavo de la Cruz Martínez

Abstract: Agile methods in undergraduate courses have been explored by various authors looking to close the gap between industry and professional profiles. We have structured an Android application development course based on a tailored agile process for development of educational software tools. This process is based on both Scrum and Extreme Programming in combination with User Experience (UX) and User-Ce… ▽ More Agile methods in undergraduate courses have been explored by various authors looking to close the gap between industry and professional profiles. We have structured an Android application development course based on a tailored agile process for development of educational software tools. This process is based on both Scrum and Extreme Programming in combination with User Experience (UX) and User-Centered Design (UCD) approaches. The course is executed in two phases: the first half of the course's semester presents theory on agile and mobile applications development, the latter half is managed as a workshop where students develop for an actual client. The introduction of UX and UCD exploiting the close relationship with stakeholders expected from an agile process can enhance Quality in Use features. Since 2019 two of the projects have been extended in agreement between the client and students. Students, clients and users have found value in the generated products. △ Less

Submitted 14 August, 2023; originally announced August 2023.

Comments: 13 pages, 5 figures, conference

Journal ref: International Journal on Cybernetics & Informatics, vol. 12, no. 5, october 2023, pp. 93-105

Analysing Mechanisms for Virtual Channel Management in Low-Diameter networks

Authors: Alejandro Cano, Cristóbal Camarero, Carmen Martínez, Ramón Beivide

Abstract: To interconnect their growing number of servers, current supercomputers and data centers are starting to adopt low-diameter networks, such as HyperX, Dragonfly and Dragonfly+. These emergent topologies require balancing the load over their links and finding suitable non-minimal routing mechanisms for them becomes particularly challenging. The Valiant load balancing scheme is a very popular choice… ▽ More To interconnect their growing number of servers, current supercomputers and data centers are starting to adopt low-diameter networks, such as HyperX, Dragonfly and Dragonfly+. These emergent topologies require balancing the load over their links and finding suitable non-minimal routing mechanisms for them becomes particularly challenging. The Valiant load balancing scheme is a very popular choice for non-minimal routing. Evolved adaptive routing mechanisms implemented in real systems are based on this Valiant scheme. All these low-diameter networks are deadlock-prone when non-minimal routing is employed. Routing deadlocks occur when packets cannot progress due to cyclic dependencies. Therefore, developing efficient deadlock-free packet routing mechanisms is critical for the progress of these emergent networks. The routing function includes the routing algorithm for path selection and the buffers management policy that dictates how packets allocate the buffers of the switches on their paths. For the same routing algorithm, a different buffer management mechanism can lead to a very different performance. Moreover, certain mechanisms considered efficient for avoiding deadlocks, may still suffer from hard to pinpoint instabilities that make erratic the network response. This paper focuses on exploring the impact of these buffers management policies on the performance of current interconnection networks, showing a 90\% of performance drop if an incorrect buffers management policy is used. Moreover, this study not only characterizes some of these undesirable scenarios but also proposes practicable solutions. △ Less

Submitted 1 February, 2024; v1 submitted 22 June, 2023; originally announced June 2023.

Adversarial Machine Learning and Cybersecurity: Risks, Challenges, and Legal Implications

Authors: Micah Musser, Andrew Lohn, James X. Dempsey, Jonathan Spring, Ram Shankar Siva Kumar, Brenda Leong, Christina Liaghati, Cindy Martinez, Crystal D. Grant, Daniel Rohrer, Heather Frase, Jonathan Elliott, John Bansemer, Mikel Rodriguez, Mitt Regan, Rumman Chowdhury, Stefan Hermanek

Abstract: In July 2022, the Center for Security and Emerging Technology (CSET) at Georgetown University and the Program on Geopolitics, Technology, and Governance at the Stanford Cyber Policy Center convened a workshop of experts to examine the relationship between vulnerabilities in artificial intelligence systems and more traditional types of software vulnerabilities. Topics discussed included the extent… ▽ More In July 2022, the Center for Security and Emerging Technology (CSET) at Georgetown University and the Program on Geopolitics, Technology, and Governance at the Stanford Cyber Policy Center convened a workshop of experts to examine the relationship between vulnerabilities in artificial intelligence systems and more traditional types of software vulnerabilities. Topics discussed included the extent to which AI vulnerabilities can be handled under standard cybersecurity processes, the barriers currently preventing the accurate sharing of information about AI vulnerabilities, legal issues associated with adversarial attacks on AI systems, and potential areas where government support could improve AI vulnerability management and mitigation. This report is meant to accomplish two things. First, it provides a high-level discussion of AI vulnerabilities, including the ways in which they are disanalogous to other types of vulnerabilities, and the current state of affairs regarding information sharing and legal oversight of AI vulnerabilities. Second, it attempts to articulate broad recommendations as endorsed by the majority of participants at the workshop. △ Less

Submitted 23 May, 2023; originally announced May 2023.

Graph Neural Network contextual embedding for Deep Learning on Tabular Data

Authors: Mario Villaizán-Vallelado, Matteo Salvatori, Belén Carro Martinez, Antonio Javier Sanchez Esguevillas

Abstract: All industries are trying to leverage Artificial Intelligence (AI) based on their existing big data which is available in so called tabular form, where each record is composed of a number of heterogeneous continuous and categorical columns also known as features. Deep Learning (DL) has constituted a major breakthrough for AI in fields related to human skills like natural language processing, but i… ▽ More All industries are trying to leverage Artificial Intelligence (AI) based on their existing big data which is available in so called tabular form, where each record is composed of a number of heterogeneous continuous and categorical columns also known as features. Deep Learning (DL) has constituted a major breakthrough for AI in fields related to human skills like natural language processing, but its applicability to tabular data has been more challenging. More classical Machine Learning (ML) models like tree-based ensemble ones usually perform better. This paper presents a novel DL model using Graph Neural Network (GNN) more specifically Interaction Network (IN), for contextual embedding and modelling interactions among tabular features. Its results outperform those of a recently published survey with DL benchmark based on five public datasets, also achieving competitive results when compared to boosted-tree solutions. △ Less

Submitted 4 July, 2023; v1 submitted 11 March, 2023; originally announced March 2023.

Do Multi-Document Summarization Models Synthesize?

Authors: Jay DeYoung, Stephanie C. Martinez, Iain J. Marshall, Byron C. Wallace

Abstract: Multi-document summarization entails producing concise synopses of collections of inputs. For some applications, the synopsis should accurately synthesize inputs with respect to a key aspect, e.g., a synopsis of film reviews written about a particular movie should reflect the average critic consensus. As a more consequential example, narrative summaries that accompany biomedical systematic reviews… ▽ More Multi-document summarization entails producing concise synopses of collections of inputs. For some applications, the synopsis should accurately synthesize inputs with respect to a key aspect, e.g., a synopsis of film reviews written about a particular movie should reflect the average critic consensus. As a more consequential example, narrative summaries that accompany biomedical systematic reviews of clinical trial results should accurately summarize the potentially conflicting results from individual trials. In this paper we ask: To what extent do modern multi-document summarization models implicitly perform this sort of synthesis? We run experiments over opinion and evidence synthesis datasets using a suite of summarization models, from fine-tuned transformers to GPT-4. We find that existing models partially perform synthesis, but imperfectly: even the best performing models are over-sensitive to changes in input ordering and under-sensitive to changes in input compositions (e.g., ratio of positive to negative reviews). We propose a simple, general, effective method for improving model synthesis capabilities by generating an explicitly diverse set of candidate outputs, and then selecting from these the string best aligned with the expected aggregate measure for the inputs, or abstaining when the model produces no good candidate. △ Less

Submitted 12 July, 2024; v1 submitted 31 January, 2023; originally announced January 2023.

Comments: Accepted to TACL, to be presented at ACL 2024 in Bangkok, Thailand. 9 Figures, 11 Tables, 14 pages of main content, 20 pages total. This paper has some _history_. Buy me a drink if you want to hear about it

Report number: TACL 6011

Evaluation of Position and Velocity Based Forward Dynamics Compliance Control (FDCC) for Robotic Interactions in Position Controlled Robots

Authors: Mohatashem Reyaz Makhdoomi, Vivek Muralidharan, Juan Sandoval, Miguel Olivares-Mendez, Carol Martinez

Abstract: In robotic manipulation, end-effector compliance is an essential precondition for performing contact-rich tasks, such as machining, assembly, and human-robot interaction. Most robotic arms are position-controlled stiff systems at a hardware level. Thus, adding compliance becomes essential. Compliance in those systems has been recently achieved using Forward dynamics compliance control (FDCC), whic… ▽ More In robotic manipulation, end-effector compliance is an essential precondition for performing contact-rich tasks, such as machining, assembly, and human-robot interaction. Most robotic arms are position-controlled stiff systems at a hardware level. Thus, adding compliance becomes essential. Compliance in those systems has been recently achieved using Forward dynamics compliance control (FDCC), which, owing to its virtual forward dynamics model, can be implemented on both position and velocity-controlled robots. This paper evaluates the choice of control interface (and hence the control domain), which, although considered trivial, is essential due to differences in their characteristics. In some cases, the choice is restricted to the available hardware interface. However, given the option to choose, the velocity-based control interface makes a better candidate for compliance control because of smoother compliant behaviour, reduced interaction forces, and work done. To prove these points, in this paper FDCC is evaluated on the UR10e six-DOF manipulator with velocity and position control modes. The evaluation is based on force-control benchmarking metrics using 3D-printed artefacts. Real experiments favour the choice of velocity control over position control. △ Less

Submitted 24 October, 2022; originally announced October 2022.

Comments: Submitted to RA-L on 15th Sept 2022, for associated video see: https://www.youtube.com/watch?v=iIFscA-CHRU

Emulating On-Orbit Interactions Using Forward Dynamics Based Cartesian Motion

Authors: Mohatashem Reyaz Makhdoomi, Vivek Muralidharan, Kuldeep R. Barad, Juan Sandoval, Miguel Olivares-Mendez, Carol Martinez

Abstract: On-orbit operations such as servicing and assembly are considered a priority for the future space industry. Ground-based facilities that emulate on-orbit interactions are key tools for developing and testing space technology. This paper presents a control framework to emulate on-orbit operations using on-ground robotic manipulators. It combines Virtual Forward Dynamics Models (VFDM) for Cartesian… ▽ More On-orbit operations such as servicing and assembly are considered a priority for the future space industry. Ground-based facilities that emulate on-orbit interactions are key tools for developing and testing space technology. This paper presents a control framework to emulate on-orbit operations using on-ground robotic manipulators. It combines Virtual Forward Dynamics Models (VFDM) for Cartesian motion control of robotic manipulators with an Orbital Dynamics Simulator (ODS) based on the Clohessy Wiltshire (CW) Model. The VFDM-based Inverse Kinematics (IK) solver is known to have better motion tracking, path accuracy, and solver convergency than traditional IK solvers. Thus, it provides a stable Cartesian motion for manipulators based on orbit emulations, even at singular or near singular configurations. The framework is tested at the ZeroG-Lab robotic facility of the SnT by emulating two scenarios: free-floating satellite motion and free-floating interaction (collision). Results show fidelity between the simulated motion commanded by the ODS and the one executed by the robot-mounted mockups. △ Less

Submitted 17 November, 2023; v1 submitted 30 September, 2022; originally announced September 2022.

Comments: Submitted to EuroGNC 2024

Mathematical Models to Analyze Lua Hybrid Tables and Why They Need a Fix

Authors: Conrado Martínez, Cyril Nicaud, Pablo Rotondo

Abstract: Lua (Ierusalimschy et al., 1996) is a well-known scripting language, popular among many programmers, most notably in the gaming industry. Remarkably, the only data-structuring mechanism in Lua are associative arrays, called tables. With Lua 5.0, the reference implementation of Lua introduced hybrid tables to implement tables using both a hashmap and a dynamically growing array combined together: t… ▽ More Lua (Ierusalimschy et al., 1996) is a well-known scripting language, popular among many programmers, most notably in the gaming industry. Remarkably, the only data-structuring mechanism in Lua are associative arrays, called tables. With Lua 5.0, the reference implementation of Lua introduced hybrid tables to implement tables using both a hashmap and a dynamically growing array combined together: the values associated with integer keys are stored in the array part, when suitable, everything else is stored in the hashmap. All this is transparent to the user, who gets a unique simple interface to handle tables. In this paper we carry out a theoretical analysis of the performance of Lua's tables, by considering various worst-case and probabilistic scenarios. In particular, we uncover some problematic situations for the simple probabilistic model where we add a new key with some fixed probability $p>\frac12$ and delete a key with probability $1-p$: the cost of performing T such operations is proved to be $Ω(T\log T)$ with high probability, where linear complexity is expected instead. △ Less

Submitted 6 December, 2023; v1 submitted 29 August, 2022; originally announced August 2022.

Comments: Long version of https://doi.org/10.1007/978-3-031-22105-7_34

Lessons from a Space Lab -- An Image Acquisition Perspective

Authors: Leo Pauly, Michele Lynn Jamrozik, Miguel Ortiz Del Castillo, Olivia Borgue, Inder Pal Singh, Mohatashem Reyaz Makhdoomi, Olga-Orsalia Christidi-Loumpasefski, Vincent Gaudilliere, Carol Martinez, Arunkumar Rathinam, Andreas Hein, Miguel Olivares-Mendez, Djamila Aouada

Abstract: The use of Deep Learning (DL) algorithms has improved the performance of vision-based space applications in recent years. However, generating large amounts of annotated data for training these DL algorithms has proven challenging. While synthetically generated images can be used, the DL models trained on synthetic data are often susceptible to performance degradation, when tested in real-world env… ▽ More The use of Deep Learning (DL) algorithms has improved the performance of vision-based space applications in recent years. However, generating large amounts of annotated data for training these DL algorithms has proven challenging. While synthetically generated images can be used, the DL models trained on synthetic data are often susceptible to performance degradation, when tested in real-world environments. In this context, the Interdisciplinary Center of Security, Reliability and Trust (SnT) at the University of Luxembourg has developed the 'SnT Zero-G Lab', for training and validating vision-based space algorithms in conditions emulating real-world space environments. An important aspect of the SnT Zero-G Lab development was the equipment selection. From the lessons learned during the lab development, this article presents a systematic approach combining market survey and experimental analyses for equipment selection. In particular, the article focus on the image acquisition equipment in a space lab: background materials, cameras and illumination lamps. The results from the experiment analyses show that the market survey complimented by experimental analyses is required for effective equipment selection in a space lab development project. △ Less

Submitted 6 December, 2022; v1 submitted 18 August, 2022; originally announced August 2022.

Journal ref: International Journal of Aerospace Engineering, vol. 2023, Article ID 9944614, 16 pages, 2023

Vision-Based Safety System for Barrierless Human-Robot Collaboration

Authors: Lina María Amaya-Mejía, Nicolás Duque-Suárez, Daniel Jaramillo-Ramírez, Carol Martinez

Abstract: Human safety has always been the main priority when working near an industrial robot. With the rise of Human-Robot Collaborative environments, physical barriers to avoiding collisions have been disappearing, increasing the risk of accidents and the need for solutions that ensure a safe Human-Robot Collaboration. This paper proposes a safety system that implements Speed and Separation Monitoring (S… ▽ More Human safety has always been the main priority when working near an industrial robot. With the rise of Human-Robot Collaborative environments, physical barriers to avoiding collisions have been disappearing, increasing the risk of accidents and the need for solutions that ensure a safe Human-Robot Collaboration. This paper proposes a safety system that implements Speed and Separation Monitoring (SSM) type of operation. For this, safety zones are defined in the robot's workspace following current standards for industrial collaborative robots. A deep learning-based computer vision system detects, tracks, and estimates the 3D position of operators close to the robot. The robot control system receives the operator's 3D position and generates 3D representations of them in a simulation environment. Depending on the zone where the closest operator was detected, the robot stops or changes its operating speed. Three different operation modes in which the human and robot interact are presented. Results show that the vision-based system can correctly detect and classify in which safety zone an operator is located and that the different proposed operation modes ensure that the robot's reaction and stop time are within the required time limits to guarantee safety. △ Less

Submitted 3 August, 2022; originally announced August 2022.

Comments: Accepted for publication at the 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning

Authors: Andrej Orsula, Simon Bøgh, Miguel Olivares-Mendez, Carol Martinez

Abstract: Extraterrestrial rovers with a general-purpose robotic arm have many potential applications in lunar and planetary exploration. Introducing autonomy into such systems is desirable for increasing the time that rovers can spend gathering scientific data and collecting samples. This work investigates the applicability of deep reinforcement learning for vision-based robotic grasping of objects on the… ▽ More Extraterrestrial rovers with a general-purpose robotic arm have many potential applications in lunar and planetary exploration. Introducing autonomy into such systems is desirable for increasing the time that rovers can spend gathering scientific data and collecting samples. This work investigates the applicability of deep reinforcement learning for vision-based robotic grasping of objects on the Moon. A novel simulation environment with procedurally-generated datasets is created to train agents under challenging conditions in unstructured scenes with uneven terrain and harsh illumination. A model-free off-policy actor-critic algorithm is then employed for end-to-end learning of a policy that directly maps compact octree observations to continuous actions in Cartesian space. Experimental evaluation indicates that 3D data representations enable more effective learning of manipulation skills when compared to traditionally used image-based observations. Domain randomization improves the generalization of learned policies to novel scenes with previously unseen objects and different illumination conditions. To this end, we demonstrate zero-shot sim-to-real transfer by evaluating trained agents on a real robot in a Moon-analogue facility. △ Less

Submitted 1 August, 2022; originally announced August 2022.

Comments: Accepted for publication at the 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) | The source code is available at https://github.com/AndrejOrsula/drl_grasping | The supplementary video is available at https://youtube.com/watch?v=FZSoOkK6VFc

Journal ref: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4112-4119

Low-Complexity Loeffler DCT Approximations for Image and Video Coding

Authors: D. F. G. Coelho, R. J. Cintra, F. M. Bayer, S. Kulasekera, A. Madanayake, P. A. C. Martinez, T. L. T. Silveira, R. S. Oliveira, V. S. Dimitrov

Abstract: This paper introduced a matrix parametrization method based on the Loeffler discrete cosine transform (DCT) algorithm. As a result, a new class of eight-point DCT approximations was proposed, capable of unifying the mathematical formalism of several eight-point DCT approximations archived in the literature. Pareto-efficient DCT approximations are obtained through multicriteria optimization, where… ▽ More This paper introduced a matrix parametrization method based on the Loeffler discrete cosine transform (DCT) algorithm. As a result, a new class of eight-point DCT approximations was proposed, capable of unifying the mathematical formalism of several eight-point DCT approximations archived in the literature. Pareto-efficient DCT approximations are obtained through multicriteria optimization, where computational complexity, proximity, and coding performance are considered. Efficient approximations and their scaled 16- and 32-point versions are embedded into image and video encoders, including a JPEG-like codec and H.264/AVC and H.265/HEVC standards. Results are compared to the unmodified standard codecs. Efficient approximations are mapped and implemented on a Xilinx VLX240T FPGA and evaluated for area, speed, and power consumption. △ Less

Submitted 28 July, 2022; originally announced July 2022.

Comments: 25 pages, 11 figures, 7 tables

Journal ref: J. Low Power Electron. Appl. 2018, 8(4), 46

Prediction of speech intelligibility with DNN-based performance measures

Authors: Angel Mario Castro Martinez, Constantin Spille, Jana Roßbach, Birger Kollmeier, Bernd T. Meyer

Abstract: This paper presents a speech intelligibility model based on automatic speech recognition (ASR), combining phoneme probabilities from deep neural networks (DNN) and a performance measure that estimates the word error rate from these probabilities. This model does not require the clean speech reference nor the word labels during testing as the ASR decoding step, which finds the most likely sequence… ▽ More This paper presents a speech intelligibility model based on automatic speech recognition (ASR), combining phoneme probabilities from deep neural networks (DNN) and a performance measure that estimates the word error rate from these probabilities. This model does not require the clean speech reference nor the word labels during testing as the ASR decoding step, which finds the most likely sequence of words given phoneme posterior probabilities, is omitted. The model is evaluated via the root-mean-squared error between the predicted and observed speech reception thresholds from eight normal-hearing listeners. The recognition task consists of identifying noisy words from a German matrix sentence test. The speech material was mixed with eight noise maskers covering different modulation types, from speech-shaped stationary noise to a single-talker masker. The prediction performance is compared to five established models and an ASR-model using word labels. Two combinations of features and networks were tested. Both include temporal information either at the feature level (amplitude modulation filterbanks and a feed-forward network) or captured by the architecture (mel-spectrograms and a time-delay deep neural network, TDNN). The TDNN model is on par with the DNN while reducing the number of parameters by a factor of 37; this optimization allows parallel streams on dedicated hearing aid hardware as a forward-pass can be computed within the 10ms of each frame. The proposed model performs almost as well as the label-based model and produces more accurate predictions than the baseline models. △ Less

Submitted 17 March, 2022; originally announced March 2022.

Journal ref: Computer Speech & Language, 74, p.101329 (2022)

Unsupervised physics-informed disentanglement of multimodal data for high-throughput scientific discovery

Authors: Nathaniel Trask, Carianne Martinez, Kookjin Lee, Brad Boyce

Abstract: We introduce physics-informed multimodal autoencoders (PIMA) - a variational inference framework for discovering shared information in multimodal scientific datasets representative of high-throughput testing. Individual modalities are embedded into a shared latent space and fused through a product of experts formulation, enabling a Gaussian mixture prior to identify shared features. Sampling from… ▽ More We introduce physics-informed multimodal autoencoders (PIMA) - a variational inference framework for discovering shared information in multimodal scientific datasets representative of high-throughput testing. Individual modalities are embedded into a shared latent space and fused through a product of experts formulation, enabling a Gaussian mixture prior to identify shared features. Sampling from clusters allows cross-modal generative modeling, with a mixture of expert decoder imposing inductive biases encoding prior scientific knowledge and imparting structured disentanglement of the latent space. This approach enables discovery of fingerprints which may be detected in high-dimensional heterogeneous datasets, avoiding traditional bottlenecks related to high-fidelity measurement and characterization. Motivated by accelerated co-design and optimization of materials manufacturing processes, a dataset of lattice metamaterials from metal additive manufacturing demonstrates accurate cross modal inference between images of mesoscale topology and mechanical stress-strain response. △ Less

Submitted 7 February, 2022; originally announced February 2022.

Maximum Entropy on Erroneous Predictions (MEEP): Improving model calibration for medical image segmentation

Authors: Agostina Larrazabal, Cesar Martinez, Jose Dolz, Enzo Ferrante

Abstract: Modern deep neural networks achieved remarkable progress in medical image segmentation tasks. However, it has recently been observed that they tend to produce overconfident estimates, even in situations of high uncertainty, leading to poorly calibrated and unreliable models. In this work we introduce Maximum Entropy on Erroneous Predictions (MEEP), a training strategy for segmentation networks whi… ▽ More Modern deep neural networks achieved remarkable progress in medical image segmentation tasks. However, it has recently been observed that they tend to produce overconfident estimates, even in situations of high uncertainty, leading to poorly calibrated and unreliable models. In this work we introduce Maximum Entropy on Erroneous Predictions (MEEP), a training strategy for segmentation networks which selectively penalizes overconfident predictions, focusing only on misclassified pixels. Our method is agnostic to the neural architecture, does not increase model complexity and can be coupled with multiple segmentation loss functions. We benchmark the proposed strategy in two challenging segmentation tasks: white matter hyperintensity lesions in magnetic resonance images (MRI) of the brain, and atrial segmentation in cardiac MRI. The experimental results demonstrate that coupling MEEP with standard segmentation losses leads to improvements not only in terms of model calibration, but also in segmentation quality. △ Less

Submitted 2 June, 2023; v1 submitted 22 December, 2021; originally announced December 2021.

Comments: Accepted for publication at MICCAI 2023

Automatic tuning of hyper-parameters of reinforcement learning algorithms using Bayesian optimization with behavioral cloning

Authors: Juan Cruz Barsce, Jorge A. Palombarini, Ernesto C. Martínez

Abstract: Optimal setting of several hyper-parameters in machine learning algorithms is key to make the most of available data. To this aim, several methods such as evolutionary strategies, random search, Bayesian optimization and heuristic rules of thumb have been proposed. In reinforcement learning (RL), the information content of data gathered by the learning agent while interacting with its environment… ▽ More Optimal setting of several hyper-parameters in machine learning algorithms is key to make the most of available data. To this aim, several methods such as evolutionary strategies, random search, Bayesian optimization and heuristic rules of thumb have been proposed. In reinforcement learning (RL), the information content of data gathered by the learning agent while interacting with its environment is heavily dependent on the setting of many hyper-parameters. Therefore, the user of an RL algorithm has to rely on search-based optimization methods, such as grid search or the Nelder-Mead simplex algorithm, that are very inefficient for most RL tasks, slows down significantly the learning curve and leaves to the user the burden of purposefully biasing data gathering. In this work, in order to make an RL algorithm more user-independent, a novel approach for autonomous hyper-parameter setting using Bayesian optimization is proposed. Data from past episodes and different hyper-parameter values are used at a meta-learning level by performing behavioral cloning which helps improving the effectiveness in maximizing a reinforcement learning variant of an acquisition function. Also, by tightly integrating Bayesian optimization in a reinforcement learning agent design, the number of state transitions needed to converge to the optimal policy for a given task is reduced. Computational experiments reveal promising results compared to other manual tweaking and optimization-based approaches which highlights the benefits of changing the algorithm hyper-parameters to increase the information content of generated data. △ Less

Submitted 15 December, 2021; originally announced December 2021.

Comments: Under review at Computational Intelligence

Orthogonal Ensemble Networks for Biomedical Image Segmentation

Authors: Agostina J. Larrazabal, César Martínez, Jose Dolz, Enzo Ferrante

Abstract: Despite the astonishing performance of deep-learning based approaches for visual tasks such as semantic segmentation, they are known to produce miscalibrated predictions, which could be harmful for critical decision-making processes. Ensemble learning has shown to not only boost the performance of individual models but also reduce their miscalibration by averaging independent predictions. In this… ▽ More Despite the astonishing performance of deep-learning based approaches for visual tasks such as semantic segmentation, they are known to produce miscalibrated predictions, which could be harmful for critical decision-making processes. Ensemble learning has shown to not only boost the performance of individual models but also reduce their miscalibration by averaging independent predictions. In this scenario, model diversity has become a key factor, which facilitates individual models converging to different functional solutions. In this work, we introduce Orthogonal Ensemble Networks (OEN), a novel framework to explicitly enforce model diversity by means of orthogonal constraints. The proposed method is based on the hypothesis that inducing orthogonality among the constituents of the ensemble will increase the overall model diversity. We resort to a new pairwise orthogonality constraint which can be used to regularize a sequential ensemble training process, resulting on improved predictive performance and better calibrated model outputs. We benchmark the proposed framework in two challenging brain lesion segmentation tasks --brain tumor and white matter hyper-intensity segmentation in MR images. The experimental results show that our approach produces more robust and well-calibrated ensemble models and can deal with challenging tasks in the context of biomedical image segmentation. △ Less

Submitted 22 May, 2021; originally announced May 2021.

Comments: Accepted for publication at MICCAI 2021

From (secure) w-domination in graphs to protection of lexicographic product graphs

Authors: Abel Cabrera Martinez, Alejandro Estrada Moreno, Juan Alberto Rodriguez-Velazquez

Abstract: Let $w=(w_0,w_1, \dots,w_l)$ be a vector of nonnegative integers such that $ w_0\ge 1$. Let $G$ be a graph and $N(v)$ the open neighbourhood of $v\in V(G)$. We say that a function $f: V(G)\longrightarrow \{0,1,\dots ,l\}$ is a $w$-dominating function if $f(N(v))=\sum_{u\in N(v)}f(u)\ge w_i$ for every vertex $v$ with $f(v)=i$. The weight of $f$ is defined to be $ω(f)=\sum_{v\in V(G)} f(v)$. Given a… ▽ More Let $w=(w_0,w_1, \dots,w_l)$ be a vector of nonnegative integers such that $ w_0\ge 1$. Let $G$ be a graph and $N(v)$ the open neighbourhood of $v\in V(G)$. We say that a function $f: V(G)\longrightarrow \{0,1,\dots ,l\}$ is a $w$-dominating function if $f(N(v))=\sum_{u\in N(v)}f(u)\ge w_i$ for every vertex $v$ with $f(v)=i$. The weight of $f$ is defined to be $ω(f)=\sum_{v\in V(G)} f(v)$. Given a $w$-dominating function $f$ and any pair of adjacent vertices $v, u\in V(G)$ with $f(v)=0$ and $f(u)>0$, the function $f_{u\rightarrow v}$ is defined by $f_{u\rightarrow v}(v)=1$, $f_{u\rightarrow v}(u)=f(u)-1$ and $f_{u\rightarrow v}(x)=f(x)$ for every $x\in V(G)\setminus\{u,v\}$. We say that a $w$-dominating function $f$ is a secure $w$-dominating function if for every $v$ with $f(v)=0$, there exists $u\in N(v)$ such that $f(u)>0$ and $f_{u\rightarrow v}$ is a $w$-dominating function as well. The (secure) $w$-domination number of $G$, denoted by ($γ_{w}^s(G)$) $γ_{w}(G)$, is defined as the minimum weight among all (secure) $w$-dominating functions. In this paper, we show how the secure (total) domination number and the (total) weak Roman domination number of lexicographic product graphs $G\circ H$ are related to $γ_w^s(G)$ or $γ_w(G)$. For the case of the secure domination number and the weak Roman domination number, the decision on whether $w$ takes specific components will depend on the value of $γ_{(1,0)}^s(H)$, while in the case of the total version of these parameters, the decision will depend on the value of $γ_{(1,1)}^s(H)$. △ Less

Submitted 11 May, 2021; originally announced May 2021.

MSC Class: 05C69; 05C76

WiCV 2020: The Seventh Women In Computer Vision Workshop

Authors: Hazel Doughty, Nour Karessli, Kathryn Leonard, Boyi Li, Carianne Martinez, Azadeh Mobasher, Arsha Nagrani, Srishti Yadav

Abstract: In this paper we present the details of Women in Computer Vision Workshop - WiCV 2020, organized in alongside virtual CVPR 2020. This event aims at encouraging the women researchers in the field of computer vision. It provides a voice to a minority (female) group in computer vision community and focuses on increasingly the visibility of these researchers, both in academia and industry. WiCV believ… ▽ More In this paper we present the details of Women in Computer Vision Workshop - WiCV 2020, organized in alongside virtual CVPR 2020. This event aims at encouraging the women researchers in the field of computer vision. It provides a voice to a minority (female) group in computer vision community and focuses on increasingly the visibility of these researchers, both in academia and industry. WiCV believes that such an event can play an important role in lowering the gender imbalance in the field of computer vision. WiCV is organized each year where it provides a.) opportunity for collaboration with between researchers b.) mentorship to female junior researchers c.) financial support to presenters to overcome monetary burden and d.) large and diverse choice of role models, who can serve as examples to younger researchers at the beginning of their careers. In this paper, we present a report on the workshop program, trends over the past years, a summary of statistics regarding presenters, attendees, and sponsorship for the current workshop. △ Less

Submitted 11 January, 2021; originally announced January 2021.

Teach me to play, gamer! Imitative learning in computer games via linguistic description of complex phenomena and decision tree

Authors: Clemente Rubio-Manzano, Tomas Lermanda, CLaudia Martinez, Alejandra Segura, Christian Vidal

Abstract: In this article, we present a new machine learning model by imitation based on the linguistic description of complex phenomena. The idea consists of, first, capturing the behaviour of human players by creating a computational perception network based on the execution traces of the games and, second, representing it using fuzzy logic (linguistic variables and if-then rules). From this knowledge, a… ▽ More In this article, we present a new machine learning model by imitation based on the linguistic description of complex phenomena. The idea consists of, first, capturing the behaviour of human players by creating a computational perception network based on the execution traces of the games and, second, representing it using fuzzy logic (linguistic variables and if-then rules). From this knowledge, a set of data (dataset) is automatically created to generate a learning model based on decision trees. This model will be used later to automatically control the movements of a bot. The result is an artificial agent that mimics the human player. We have implemented, tested and evaluated this technology. The results obtained are interesting and promising, showing that this method can be a good alternative to design and implement the behaviour of intelligent agents in video game development. △ Less

Submitted 6 January, 2021; originally announced January 2021.

Perfect domination, Roman domination and perfect Roman domination in lexicographic product graphs

Authors: A. Cabrera Martinez, C. Garcia-Gomez, J. A. Rodriguez-Velazquez

Abstract: The aim of this paper is to obtain closed formulas for the perfect domination number, the Roman domination number and the perfect Roman domination number of lexicographic product graphs. We show that these formulas can be obtained relatively easily for the case of the first two parameters. The picture is quite different when it concerns the perfect Roman domination number. In this case, we obtain… ▽ More The aim of this paper is to obtain closed formulas for the perfect domination number, the Roman domination number and the perfect Roman domination number of lexicographic product graphs. We show that these formulas can be obtained relatively easily for the case of the first two parameters. The picture is quite different when it concerns the perfect Roman domination number. In this case, we obtain general bounds and then we give sufficient and/or necessary conditions for the bounds to be achieved. We also discuss the case of perfect Roman graphs and we characterize the lexicographic product graphs where the perfect Roman domination number equals the Roman domination number. △ Less

Submitted 26 April, 2022; v1 submitted 6 January, 2021; originally announced January 2021.

MSC Class: 05C69; 05C76

Journal ref: Fundamenta Informaticae, Volume 185, Issue 3 (May 6, 2022) fi:7053

Quantifying the unknown impact of segmentation uncertainty on image-based simulations

Authors: Michael C. Krygier, Tyler LaBonte, Carianne Martinez, Chance Norris, Krish Sharma, Lincoln N. Collins, Partha P. Mukherjee, Scott A. Roberts

Abstract: Image-based simulation, the use of 3D images to calculate physical quantities, fundamentally relies on image segmentation to create the computational geometry. However, this process introduces image segmentation uncertainty because there is a variety of different segmentation tools (both manual and machine-learning-based) that will each produce a unique and valid segmentation. First, we demonstrat… ▽ More Image-based simulation, the use of 3D images to calculate physical quantities, fundamentally relies on image segmentation to create the computational geometry. However, this process introduces image segmentation uncertainty because there is a variety of different segmentation tools (both manual and machine-learning-based) that will each produce a unique and valid segmentation. First, we demonstrate that these variations propagate into the physics simulations, compromising the resulting physics quantities. Second, we propose a general framework for rapidly quantifying segmentation uncertainty. Through the creation and sampling of segmentation uncertainty probability maps, we systematically and objectively create uncertainty distributions of the physics quantities. We show that physics quantity uncertainty distributions can follow a Normal distribution, but, in more complicated physics simulations, the resulting uncertainty distribution can be both nonintuitive and surprisingly nontrivial. We also establish that simply bounding the uncertainty can fail in situations that are sensitive to image segmentation. While our work does not eliminate segmentation uncertainty, it makes visible the previously unrecognized range of uncertainty currently plaguing image-based simulation, enabling more credible simulations. △ Less

Submitted 9 September, 2021; v1 submitted 17 December, 2020; originally announced December 2020.

Journal ref: Nature Communications 12, 5414 (2021)

Principles for data analysis workflows

Authors: Sara Stoudt, Valeri N. Vasquez, Ciera C. Martinez

Abstract: Traditional data science education often omits training on research workflows: the process that moves a scientific investigation from raw data to coherent research question to insightful contribution. In this paper, we elaborate basic principles of a reproducible data analysis workflow by defining three phases: the Exploratory, Refinement, and Polishing Phases. Each workflow phase is roughly cente… ▽ More Traditional data science education often omits training on research workflows: the process that moves a scientific investigation from raw data to coherent research question to insightful contribution. In this paper, we elaborate basic principles of a reproducible data analysis workflow by defining three phases: the Exploratory, Refinement, and Polishing Phases. Each workflow phase is roughly centered around the audience to whom research decisions, methodologies, and results are being immediately communicated. Importantly, each phase can also give rise to a number of research products beyond traditional academic publications. Where relevant, we draw analogies between principles for data-intensive research workflows and established practice in software development. The guidance provided here is not intended to be a strict rulebook; rather, the suggestions for practices and tools to advance reproducible, sound data-intensive analysis may furnish support for both students and current professionals. △ Less

Submitted 16 July, 2020; originally announced July 2020.

Post-DAE: Anatomically Plausible Segmentation via Post-Processing with Denoising Autoencoders

Authors: Agostina J Larrazabal, César Martínez, Ben Glocker, Enzo Ferrante

Abstract: We introduce Post-DAE, a post-processing method based on denoising autoencoders (DAE) to improve the anatomical plausibility of arbitrary biomedical image segmentation algorithms. Some of the most popular segmentation methods (e.g. based on convolutional neural networks or random forest classifiers) incorporate additional post-processing steps to ensure that the resulting masks fulfill expected co… ▽ More We introduce Post-DAE, a post-processing method based on denoising autoencoders (DAE) to improve the anatomical plausibility of arbitrary biomedical image segmentation algorithms. Some of the most popular segmentation methods (e.g. based on convolutional neural networks or random forest classifiers) incorporate additional post-processing steps to ensure that the resulting masks fulfill expected connectivity constraints. These methods operate under the hypothesis that contiguous pixels with similar aspect should belong to the same class. Even if valid in general, this assumption does not consider more complex priors like topological restrictions or convexity, which cannot be easily incorporated into these methods. Post-DAE leverages the latest developments in manifold learning via denoising autoencoders. First, we learn a compact and non-linear embedding that represents the space of anatomically plausible segmentations. Then, given a segmentation mask obtained with an arbitrary method, we reconstruct its anatomically plausible version by projecting it onto the learnt manifold. The proposed method is trained using unpaired segmentation mask, what makes it independent of intensity information and image modality. We performed experiments in binary and multi-label segmentation of chest X-ray and cardiac magnetic resonance images. We show how erroneous and noisy segmentation masks can be improved using Post-DAE. With almost no additional computation cost, our method brings erroneous segmentations back to a feasible space. △ Less

Submitted 24 June, 2020; originally announced June 2020.

Comments: Accepted for publication in IEEE Transactions on Medical Imaging (IEEE TMI)

Journal ref: IEEE Transactions on Medical Imaging (IEEE TMI), 2020

The Consistency of Trust-Sales Relationship in Latin-American E-commerce

Authors: Juan C. Correa, Henry Laverde-Rojas, Camilo A. Martinez, Oscar Javier Camargo, Gustavo Rojas-Matute, Marithza Sandoval-Escobar

Abstract: Customer's trust in vendors' reputation is a key factor that facilitates economic transactions in e-commerce platforms. Although the trust-sales relationship is assumed robust and consistent, its empirical evidence remains neglected for Latin American countries. This work aims to provide a data-driven comprehensive framework for extracting valuable knowledge from public data available in the leadi… ▽ More Customer's trust in vendors' reputation is a key factor that facilitates economic transactions in e-commerce platforms. Although the trust-sales relationship is assumed robust and consistent, its empirical evidence remains neglected for Latin American countries. This work aims to provide a data-driven comprehensive framework for extracting valuable knowledge from public data available in the leading Latin American e-commerce platform with commercial operations in 18 countries. Only Argentina, Brasil, Chile, Colombia, Ecuador, Mexico, Uruguay, and Venezuela showed the highest trust indexes among all nations analyzed. The trust-sales relationship was statistically inconsistent across nations but worked as the most important predictor of sales, followed by purchase intention and price. △ Less

Submitted 11 September, 2021; v1 submitted 1 November, 2019; originally announced November 2019.

Comments: 13 pages, 3 Figures, 3 Tables

Journal ref: Journal of Internet Commerce (2021)