Showing 1–50 of 55 results for author: Kennedy, M

Toward Human Rights Benchmarking for LLMs: A Pilot Methodology

Authors: Savannah Thais, Wm. Matthew Kennedy, Abhigyan Acherjee, Matilda Wysocki, Malcolm Langford, Caitlin Kraft Buchman

Abstract: Large language models (LLMs) increasingly mediate legal determinations over what human rights are realized, and how. Yet, no evaluation benchmark exists to assess whether they can reason correctly about human rights law. To this end, we report our efforts to develop a robust and scalable methodology for creating HumRightsBench: the first expert-validated, scenario-based benchmark for evaluating re… ▽ More Large language models (LLMs) increasingly mediate legal determinations over what human rights are realized, and how. Yet, no evaluation benchmark exists to assess whether they can reason correctly about human rights law. To this end, we report our efforts to develop a robust and scalable methodology for creating HumRightsBench: the first expert-validated, scenario-based benchmark for evaluating reasoning grounded in the obligation structure of international human rights law. We adapt the IRAC framework for legal reasoning to better suit the unique reasoning patterns of human rights work (substituting P, "proposing remedies," for C, "legal conclusion," yielding IRAP) to structure our evaluation heuristics. We also produce a pilot series of authentic scenarios designed to implicate the many dimensions of real-world human rights issues and annotated by human rights lawyers and professionals across the world. Ultimately, we find that model accuracy scores range considerably across legal reasoning tasks (overall model performance ranges from 0.339 to 0.577, task min-max ranges from 0.025 to 0.774), which strongly implies that HumRightsBench is a capable instrument for advancing this emerging subfield of AI evaluations science at a critical moment in its evolution. △ Less

Submitted 10 August, 2026; originally announced August 2026.

Comments: Best paper, honorable mention, at the ICML 2026 Workshop on AI4Law, Seoul, South Korea

L2-Bench: An Evaluation Benchmark for Measuring LLM Capabilities in Second Language Education

Authors: James Edgell, Wm. Matthew Kennedy, Ben Knight, Danielle Carvalho, Martin Ku, Isaac Pattis

Abstract: Despite rapid AI adoption in education, rigorous evaluation of AI-powered educational (AIED) systems remains critically underdeveloped, particularly in second language (L2) education, one of the most common yet least evaluated AI applications. We introduce L2-Bench, an open-source benchmark of 1,000+ task-response pairs to aid the pedagogy-led evaluation of LLM capabilities relating to language le… ▽ More Despite rapid AI adoption in education, rigorous evaluation of AI-powered educational (AIED) systems remains critically underdeveloped, particularly in second language (L2) education, one of the most common yet least evaluated AI applications. We introduce L2-Bench, an open-source benchmark of 1,000+ task-response pairs to aid the pedagogy-led evaluation of LLM capabilities relating to language learning and assessment. Crucially, L2-Bench measures model performativity on the application of learning experience design principles rather than mere knowledge of those principles or broad learning outcomes. Our contributions include: (1) a validated taxonomy of 12 competencies and 31 subcompetencies validated by 200+ expert practitioners (task authenticity: 4.42/5.00, criteria adequacy: 4.18/5.00); (2) a rubric-based evaluation methodology that we believe can, if adapted, generalize to similar (open-ended, qualitative) disciplines; (3) an evaluation dataset that produces reliable signal about model strengths, weaknesses, and contextual robustness across diverse L2 education scenarios. We find that, among large models, Claude Opus 4.7 performs best overall (85.5%), though is marginally outperformed on several constituent tasks. We also find that performance drops notably on harder tasks (69.9% to 73.4%). L2-Bench provides education stakeholders better methods to make more informed decisions about real-world AIED adoption, use, and governance, while advancing the maturing science of AI evaluations for education. △ Less

Submitted 15 July, 2026; v1 submitted 9 July, 2026; originally announced July 2026.

Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results

Authors: Jan Batzner, Sree Harsha Nelaturu, Damian Stachura, Anastassia Kornilova, Jon Crall, Tommaso Cerruti, Yanan Long, Yifan Mai, Sanchit Ahuja, Asaf Yehudai, Marek Šuppa, John P. Lalor, Oluwagbemike Olowe, Jatin Ganhotra, Brian H. Hu, Eliya Habba, Andrew M. Bean, Chang Liu, Sander Land, Steven Dillmann, Aniketh Garikaparthi, Elron Bandel, Saki Imai, James Edgell, Wm. Matthew Kennedy , et al. (23 additional authors not shown)

Abstract: AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First, results are saved in incompatible formats, scattered across leaderboards, papers, blog posts, evaluation harness logs, and custom repositories. Second, results are created by different evaluation frameworks, which prod… ▽ More AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First, results are saved in incompatible formats, scattered across leaderboards, papers, blog posts, evaluation harness logs, and custom repositories. Second, results are created by different evaluation frameworks, which produce divergent scores for nominally identical evaluations and record metadata inconsistently, hindering comparison, cross-community evaluation science, cost reduction, and reuse. We introduce Every Eval Ever, the first shared schema and community-crowdsourced repository for AI evaluation results. The schema standardizes how evaluations are represented in a unified, single JSON document. It is source-agnostic by design, ingesting results from evaluation harnesses and papers alike, and optionally stores per-instance outputs for fine-grained analysis. We contribute: (i) a community-governed metadata schema with a companion instance-level schema, the first standardization effort of its kind; (ii) automatic converters from popular formats, evaluation harnesses, and leaderboards to the unified schema; and (iii) a crowdsourced community database hosted on Hugging Face, currently spanning to date 22,235 models, 2,273 unique benchmarks, and 31 evaluation formats. △ Less

Submitted 12 June, 2026; originally announced June 2026.

Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting

Authors: Avijit Ghosh, Anka Reuel, Jenny Chim, Wm. Matthew Kennedy, Srishti Yadav, Jennifer Mickel, Yanan Long, Andrew Tran, Anastassia Kornilova, Damian Stachura, Kevin Klyman, Felix Friedrich, Jeba Sania, Jan Batzner, Anoop Mishra, Eliya Habba, Yixiong Hao, Nathan Heath, Shalaleh Rismani, Usman Gohar, Andrea Loehr, David Manheim, Ruchira Dhar, Sree Harsha Nelaturu, Aarush Sinha , et al. (23 additional authors not shown)

Abstract: AI evaluation results are produced at scale but reported inconsistently across leaderboards, model cards, benchmark papers, and company blogs. The cost is interpretive: readers cannot reliably compare results across sources, identify what a report omits, or trace an aggregate claim to its underlying evidence. Recent efforts address isolated components but leave three gaps: they cover only narrow s… ▽ More AI evaluation results are produced at scale but reported inconsistently across leaderboards, model cards, benchmark papers, and company blogs. The cost is interpretive: readers cannot reliably compare results across sources, identify what a report omits, or trace an aggregate claim to its underlying evidence. Recent efforts address isolated components but leave three gaps: they cover only narrow slices of the evaluation lifecycle and do not compose into a single interpretable record; they specify static representations that do not differentiate the questions different stakeholders bring to the same evidence; and they remain proposals on paper, lacking the extraction infrastructure required for adoption at scale. We present \EvalCards{}, an operational reporting layer that composes benchmark metadata, evaluation run data, and model metadata into a unified record. We (1) derive a reporting schema from a structured review of 52 papers and 10 stakeholder interviews, (2) implement four interpretive signals (reproducibility, documentation completeness, provenance and risk, and score comparability), rendered through reader modes calibrated to research and non-research audiences, and (3) deploy a monitoring tool that applies \EvalCards{} across 5,816 models, 635 benchmarks, and 101,843 results, surfacing systematic gaps in current reporting practice. △ Less

Submitted 9 June, 2026; v1 submitted 8 June, 2026; originally announced June 2026.

DOT-Sim: Differentiable Optical Tactile Simulation with Precise Real-to-Sim Physical Calibration

Authors: Yang You, Won Kyung Do, Aiden Swann, Rika Antonova, Monroe Kennedy, Leonidas Guibas

Abstract: Simulating optical tactile sensors presents significant challenges due to their high deformability and intricate optical properties. To address these issues and enable a physically accurate simulation, we propose DOT-Sim: Differentiable Optical Tactile Simulation. Unlike prior simulators that rely on simplified models of deformable sensors, DOT-Sim accurately captures the physical behavior of soft… ▽ More Simulating optical tactile sensors presents significant challenges due to their high deformability and intricate optical properties. To address these issues and enable a physically accurate simulation, we propose DOT-Sim: Differentiable Optical Tactile Simulation. Unlike prior simulators that rely on simplified models of deformable sensors, DOT-Sim accurately captures the physical behavior of soft sensors by modeling them as elastic materials using the Material Point Method (MPM). DOT-Sim enables rapid calibration of optical tactile sensor simulation using a small number of demonstrations within minutes, which is substantially faster than existing methods. Compared to current baselines, our approach supports much larger and non-linear deformations. To handle the optical aspect, we propose a novel approach to simulating optical responses by learning a residual image relative to the real-world idle state. We validate the physical and visual realism of our method through a series of zero-shot sim-to-real tasks. Our experiments show that DOT-Sim (1) accurately replicates the physical dynamics of a DenseTact optical tactile sensor in reality, (2) generates realistic optical outputs in contact-rich scenarios, (3) enables direct deployment of simulation-trained classifiers in the real world, achieving 85% classification accuracy on challenging objects and 90% accuracy in embedded tumor-type detection, and (4) allows precise trajectory following with a policy trained from demonstrations in simulation, with an average error of less than 0.9 mm. △ Less

Submitted 29 April, 2026; originally announced April 2026.

Comments: Accepted at ICRA 2026

Ceci n'est pas une explication: Evaluating Explanation Failures as Explainability Pitfalls in Language Learning Systems

Authors: Ben Knight, Wm. Matthew Kennedy, Danielle Carvalho, Isaac Pattis, James Edgell

Abstract: AI-powered language learning tools increasingly provide instant, personalised feedback to millions of learners worldwide. However, this feedback can fail in ways that are difficult for learners--and even teachers--to detect, potentially reinforcing misconceptions and eroding learning outcomes over extended use. We present a portion of L2-Bench, a benchmark for evaluating AI systems in language edu… ▽ More AI-powered language learning tools increasingly provide instant, personalised feedback to millions of learners worldwide. However, this feedback can fail in ways that are difficult for learners--and even teachers--to detect, potentially reinforcing misconceptions and eroding learning outcomes over extended use. We present a portion of L2-Bench, a benchmark for evaluating AI systems in language education that includes (but is not limited to) six critical dimensions of effective feedback: diagnostic accuracy, awareness of appropriacy, causes of error, prioritisation, guidance for improvement, and supporting self-regulation. We analyse how AI systems can fail with respect to these dimensions. These failures, which we argue are conducive to "explainability pitfalls," are AI-generated explanations that appear helpful on the surface but are fundamentally flawed, increasing the risk of attainment, human-AI interaction, and socioaffective harms. We discuss how the specific context of language learning amplifies these risks and outline open questions we believe merit more attention when designing evaluation frameworks specifically. Our analysis aims to expand the community's understanding of both the typology of explainability pitfalls and the contextual dynamics in which they may occur in order to encourage AI developers to better design safe, trustworthy, and effective AI explanations. △ Less

Submitted 22 May, 2026; v1 submitted 28 April, 2026; originally announced April 2026.

Comments: Accepted to Misleading Impacts Resulting from AI Generated Explanations (MIRAGE) Workshop @ IUI 2026

Learning Humanoid Navigation from Human Data

Authors: Weizhuo Wang, Yanjie Ze, C. Karen Liu, Monroe Kennedy III

Abstract: We present EgoNav, a system that enables a humanoid robot to traverse diverse, unseen environments by learning entirely from 5 hours of human walking data, with no robot data or finetuning. A diffusion model predicts distributions of plausible future trajectories conditioned on past trajectory, a 360 deg visual memory fusing color, depth, and semantics, and video features from a frozen DINOv3 back… ▽ More We present EgoNav, a system that enables a humanoid robot to traverse diverse, unseen environments by learning entirely from 5 hours of human walking data, with no robot data or finetuning. A diffusion model predicts distributions of plausible future trajectories conditioned on past trajectory, a 360 deg visual memory fusing color, depth, and semantics, and video features from a frozen DINOv3 backbone that capture appearance cues invisible to depth sensors. A hybrid sampling scheme achieves real-time inference in 10 denoising steps, and a receding-horizon controller selects paths from the predicted distribution. We validate EgoNav through offline evaluations, where it outperforms baselines in collision avoidance and multi-modal coverage, and through zero-shot deployment on a Unitree G1 humanoid across unseen indoor and outdoor environments. Behaviors such as waiting for doors to open, navigating around crowds, and avoiding glass walls emerge naturally from the learned prior. We will release the dataset and trained models. Our website: https://egonav.weizhuowang.com △ Less

Submitted 31 March, 2026; originally announced April 2026.

Comments: 8 pages 8 figures

Towards an Evaluation Methodology for AI in Second Language Education: Lessons Learned from Developing L2-Bench

Authors: James Edgell, Wm. Matthew Kennedy, Isaac Pattis, Ben Knight, Danielle Carvalho, Elizabeth Wonnacott

Abstract: The rapid adoption of large language models in AI-powered language education has created an urgent need for evaluations that assess pedagogical effectiveness, particularly in language learning--one of the most common LLM use cases (Tamkin et al. 2024; Costa-Gomes et al. 2025). With only narrowly defined task-specific evaluations of AI system capabilities in second language (L2) education existing… ▽ More The rapid adoption of large language models in AI-powered language education has created an urgent need for evaluations that assess pedagogical effectiveness, particularly in language learning--one of the most common LLM use cases (Tamkin et al. 2024; Costa-Gomes et al. 2025). With only narrowly defined task-specific evaluations of AI system capabilities in second language (L2) education existing in the literature, we require more holistic approaches in this AI for education space. To address this gap, we describe the iteration of the methodology we developed to build L2-Bench, a novel, context-specific evaluation benchmark grounded in a validated "language learning experience designer" construct to assess AI capabilities across L2 education contexts. Our methodology integrates pedagogical theory, sociotechnical AI evaluation methods, and operationalizes a hierarchical taxonomy to structure an expert-curated dataset of over 1,000 authentic rubric-scored task-response pairs with measurement and scoring pipeline. We report the results of a pilot validation exercise (N = 39) on an initial sample of our dataset (tasks were validated as authentic [M = 4.23/5], but criteria scores were lower [M = 3.94], with universally poor inter-annotator agreement despite good internal consistency), alongside the experimental design for our follow-up practitioner data validation study as we iterate and scale to the full dataset. Ultimately, this research not only offers methodological lessons towards a more context-specific AI evaluations ecosystem, but also works towards better design of reproducible evaluations for AI systems deployed to educational contexts △ Less

Submitted 22 May, 2026; v1 submitted 20 March, 2026; originally announced March 2026.

Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models

Authors: Aiden Swann, Lachlain McGranahan, Hugo Buurmeijer, Monroe Kennedy III, Mac Schwager

Abstract: Vision-Language-Action (VLA) models have emerged as a promising approach for general-purpose robot manipulation. However, little research has mechanistically explored when and why they generalize across objects, scenes, and instructions. To probe internal representations, we train Sparse Autoencoders (SAEs) on the VLA's hidden-layer activations. SAEs learn sparse dictionaries over model activation… ▽ More Vision-Language-Action (VLA) models have emerged as a promising approach for general-purpose robot manipulation. However, little research has mechanistically explored when and why they generalize across objects, scenes, and instructions. To probe internal representations, we train Sparse Autoencoders (SAEs) on the VLA's hidden-layer activations. SAEs learn sparse dictionaries over model activations, often revealing features that correspond to interpretable directions in the model's representation space. We identify SAE features corresponding to motion primitives and semantic concepts, including features that are general across episodes and causally steerable. We propose a metric to categorize features as general transferable primitives or episode-specific memorizations, offering a promising glimpse towards VLA generalization. We validate these findings through steering experiments on both the LIBERO simulation benchmark and on real-world DROID hardware. We find that amplifying general and semantic features induces behaviors consistent with their meanings, whereas ablating them destroys model performance. Furthermore, we demonstrate steering as a way to control behavior in unpromptable directions. Together, these results provide mechanistic evidence that VLAs can learn reusable internal features linking perception, language, and action across tasks and scenes. Our project page is located at https://drvla.github.io △ Less

Submitted 6 June, 2026; v1 submitted 19 March, 2026; originally announced March 2026.

Comments: 24 pages, 11 figures

CalmReminder: A Design Probe for Parental Engagement with Children with Hyperactivity, Augmented by Real-Time Motion Sensing with a Watch

Authors: Riku Arakawa, Shreya Bali, Anupama Sitaraman, Woosuk Seo, Sam Shaaban, Oliver Lindheim, Traci M. Kennedy, Mayank Goel

Abstract: Families raising children with ADHD often experience heightened stress and reactive parenting. While digital interventions promise personalization, many remain one-size-fits-all and fail to reflect parents' lived practices. We present CalmReminder, a watch-based system that detects children's calm moments and delivers just-in-time prompts to parents. Through a four-week deployment with 16 families… ▽ More Families raising children with ADHD often experience heightened stress and reactive parenting. While digital interventions promise personalization, many remain one-size-fits-all and fail to reflect parents' lived practices. We present CalmReminder, a watch-based system that detects children's calm moments and delivers just-in-time prompts to parents. Through a four-week deployment with 16 families (twelve completed) of children with ADHD, we compared notification strategies ranging from hourly to random to only when the child was inferred to be calm. Our sensing-based notifications were frequently perceived as arriving during calm moments. More importantly, parents adopted the system in diverse ways: using notifications for praise, mindfulness, activity planning, or conversation. These findings show that parents are not passive recipients but active designers, reshaping interventions to fit their parenting styles. We contribute a calm detection pipeline, empirical insights into families' flexible appropriation of notifications, and design implications for intervention systems that foster agency. △ Less

Submitted 25 February, 2026; v1 submitted 18 February, 2026; originally announced February 2026.

Comments: Accepted by ACM CHI Conference on Human Factors in Computing Systems(CHI'26)

Left, Right, or Center? Evaluating LLM Framing in News Classification and Generation

Authors: Molly Kennedy, Ali Parker, Yihong Liu, Hinrich Schütze

Abstract: Large Language Model (LLM) based summarization and text generation are increasingly used for producing and rewriting text, raising concerns about political framing in journalism where subtle wording choices can shape interpretation. Across nine state-of-the-art LLMs, we study political framing by testing whether LLMs' classification-based bias signals align with framing behavior in their generated… ▽ More Large Language Model (LLM) based summarization and text generation are increasingly used for producing and rewriting text, raising concerns about political framing in journalism where subtle wording choices can shape interpretation. Across nine state-of-the-art LLMs, we study political framing by testing whether LLMs' classification-based bias signals align with framing behavior in their generated summaries. We first compare few-shot ideology predictions against LEFT/CENTER/RIGHT labels. We then generate "steered" summaries under FAITHFUL, CENTRIST, LEFT, and RIGHT prompts, and score all outputs using a single fixed ideology evaluator. We find pervasive ideological center-collapse in both article-level ratings and generated text, indicating a systematic tendency toward centrist framing. Among evaluated models, Grok 4 is by far the most ideologically expressive generator, while Claude Sonnet 4.5 and Llama 3.1 achieve the strongest bias-rating performance among commercial and open-weight models, respectively. △ Less

Submitted 9 January, 2026; originally announced January 2026.

Locomotion Beyond Feet

Authors: Tae Hoon Yang, Haochen Shi, Jiacheng Hu, Zhicong Zhang, Daniel Jiang, Weizhuo Wang, Yao He, Zhen Wu, Yuming Chen, Yifan Hou, Monroe Kennedy III, Shuran Song, C. Karen Liu

Abstract: Most locomotion methods for humanoid robots focus on leg-based gaits, yet natural bipeds frequently rely on hands, knees, and elbows to establish additional contacts for stability and support in complex environments. This paper introduces Locomotion Beyond Feet, a comprehensive system for whole-body humanoid locomotion across extremely challenging terrains, including low-clearance spaces under cha… ▽ More Most locomotion methods for humanoid robots focus on leg-based gaits, yet natural bipeds frequently rely on hands, knees, and elbows to establish additional contacts for stability and support in complex environments. This paper introduces Locomotion Beyond Feet, a comprehensive system for whole-body humanoid locomotion across extremely challenging terrains, including low-clearance spaces under chairs, knee-high walls, knee-high platforms, and steep ascending and descending stairs. Our approach addresses two key challenges: contact-rich motion planning and generalization across diverse terrains. To this end, we combine physics-grounded keyframe animation with reinforcement learning. Keyframes encode human knowledge of motor skills, are embodiment-specific, and can be readily validated in simulation or on hardware, while reinforcement learning transforms these references into robust, physically accurate motions. We further employ a hierarchical framework consisting of terrain-specific motion-tracking policies, failure recovery mechanisms, and a vision-based skill planner. Real-world experiments demonstrate that Locomotion Beyond Feet achieves robust whole-body locomotion and generalizes across obstacle sizes, obstacle instances, and terrain sequences. △ Less

Submitted 7 January, 2026; originally announced January 2026.

Comments: Project website: https://locomotion-beyond-feet.github.io/

The Role of Consequential and Functional Sound in Human-Robot Interaction: Toward Audio Augmented Reality Interfaces

Authors: Aliyah Smith, Monroe Kennedy III

Abstract: Robot sound, encompassing both consequential operational noise and intentionally designed auditory cues, plays an important role in human-robot interaction (HRI). Developing a deeper understanding of how robot sounds influence human experience, and how technologies such as augmented reality (AR) modulate these effects, can enable the design of more socially acceptable robots and more effective, in… ▽ More Robot sound, encompassing both consequential operational noise and intentionally designed auditory cues, plays an important role in human-robot interaction (HRI). Developing a deeper understanding of how robot sounds influence human experience, and how technologies such as augmented reality (AR) modulate these effects, can enable the design of more socially acceptable robots and more effective, intuitive human-robot interfaces. In this work, we present a three-part mixed-methods study (N = 51) that investigates (i) the effects of consequential robot sounds on human perception under varying degrees of physical colocation, (ii) human accuracy in localizing spatial audio cues delivered via augmented reality, and (iii) the use of augmented spatial audio cues for functional and transformative communication during collaborative handover tasks, in comparison to non-AR sound designs. Contrary to prior findings, our results indicate that the consequential sounds of a Kinova Gen3 manipulator did not negatively affect participants' perceptions of the robot. Participants demonstrated high accuracy in localizing lateral spatial cues, whereas frontal cues proved more challenging, delineating conditions under which spatial auditory feedback is most effective. Qualitative findings further reveal that augmented spatial audio cues can simultaneously convey task-relevant information while fostering a sense of warmth and reducing user discomfort during interaction. Together, these findings elucidate the perceptual effects of consequential robot sound and position sound, particularly augmented spatial audio, as a meaningful yet underutilized design resource for human-robot interaction. △ Less

Submitted 25 March, 2026; v1 submitted 19 November, 2025; originally announced November 2025.

Comments: 29 pages, 11 figures

SlideBot: A Multi-Agent Framework for Generating Informative, Reliable, Multi-Modal Presentations

Authors: Eric Xie, Danielle Waterfield, Michael Kennedy, Aidong Zhang

Abstract: Large Language Models (LLMs) have shown immense potential in education, automating tasks like quiz generation and content summarization. However, generating effective presentation slides introduces unique challenges due to the complexity of multimodal content creation and the need for precise, domain-specific information. Existing LLM-based solutions often fail to produce reliable and informative… ▽ More Large Language Models (LLMs) have shown immense potential in education, automating tasks like quiz generation and content summarization. However, generating effective presentation slides introduces unique challenges due to the complexity of multimodal content creation and the need for precise, domain-specific information. Existing LLM-based solutions often fail to produce reliable and informative outputs, limiting their educational value. To address these limitations, we introduce SlideBot - a modular, multi-agent slide generation framework that integrates LLMs with retrieval, structured planning, and code generation. SlideBot is organized around three pillars: informativeness, ensuring deep and contextually grounded content; reliability, achieved by incorporating external sources through retrieval; and practicality, which enables customization and iterative feedback through instructor collaboration. It incorporates evidence-based instructional design principles from Cognitive Load Theory (CLT) and the Cognitive Theory of Multimedia Learning (CTML), using structured planning to manage intrinsic load and consistent visual macros to reduce extraneous load and enhance dual-channel learning. Within the system, specialized agents collaboratively retrieve information, summarize content, generate figures, and format slides using LaTeX, aligning outputs with instructor preferences through interactive refinement. Evaluations from domain experts and students in AI and biomedical education show that SlideBot consistently enhances conceptual accuracy, clarity, and instructional value. These findings demonstrate SlideBot's potential to streamline slide preparation while ensuring accuracy, relevance, and adaptability in higher education. △ Less

Submitted 12 November, 2025; originally announced November 2025.

Comments: 32 pages, 14 figures, accepted into EAAI 2026

Ask What Your Country Can Do For You: Towards a Public Red Teaming Model

Authors: Wm. Matthew Kennedy, Cigdem Patlak, Jayraj Dave, Blake Chambers, Aayush Dhanotiya, Darshini Ramiah, Reva Schwartz, Jack Hagen, Akash Kundu, Mouni Pendharkar, Liam Baisley, Theodora Skeadas, Rumman Chowdhury

Abstract: AI systems have the potential to produce both benefits and harms, but without rigorous and ongoing adversarial evaluation, AI actors will struggle to assess the breadth and magnitude of the AI risk surface. Researchers from the field of systems design have developed several effective sociotechnical AI evaluation and red teaming techniques targeting bias, hate speech, mis/disinformation, and other… ▽ More AI systems have the potential to produce both benefits and harms, but without rigorous and ongoing adversarial evaluation, AI actors will struggle to assess the breadth and magnitude of the AI risk surface. Researchers from the field of systems design have developed several effective sociotechnical AI evaluation and red teaming techniques targeting bias, hate speech, mis/disinformation, and other documented harm classes. However, as increasingly sophisticated AI systems are released into high-stakes sectors (such as education, healthcare, and intelligence-gathering), our current evaluation and monitoring methods are proving less and less capable of delivering effective oversight. In order to actually deliver responsible AI and to ensure AI's harms are fully understood and its security vulnerabilities mitigated, pioneering new approaches to close this "responsibility gap" are now more urgent than ever. In this paper, we propose one such approach, the cooperative public AI red-teaming exercise, and discuss early results of its prior pilot implementations. This approach is intertwined with CAMLIS itself: the first in-person public demonstrator exercise was held in conjunction with CAMLIS 2024. We review the operational design and results of this exercise, the prior National Institute of Standards and Technology (NIST)'s Assessing the Risks and Impacts of AI (ARIA) pilot exercise, and another similar exercise conducted with the Singapore Infocomm Media Development Authority (IMDA). Ultimately, we argue that this approach is both capable of delivering meaningful results and is also scalable to many AI developing jurisdictions. △ Less

Submitted 22 October, 2025; originally announced October 2025.

Cascade! Human in the loop shortcomings can increase the risk of failures in recommender systems

Authors: Wm. Matthew Kennedy, Nishanshi Shukla, Cigdem Patlak, Blake Chambers, Theodora Skeadas, Tuesday, Kingsley Owadara, Aayush Dhanotiya

Abstract: Recommender systems are among the most commonly deployed systems today. Systems design approaches to AI-powered recommender systems have done well to urge recommender system developers to follow more intentional data collection, curation, and management procedures. So too has the "human-in-the-loop" paradigm been widely adopted, primarily to address the issue of accountability. However, in this pa… ▽ More Recommender systems are among the most commonly deployed systems today. Systems design approaches to AI-powered recommender systems have done well to urge recommender system developers to follow more intentional data collection, curation, and management procedures. So too has the "human-in-the-loop" paradigm been widely adopted, primarily to address the issue of accountability. However, in this paper, we take the position that human oversight in recommender system design also entails novel risks that have yet to be fully described. These risks are "codetermined" by the information context in which such systems are often deployed. Furthermore, new knowledge of the shortcomings of "human-in-the-loop" practices to deliver meaningful oversight of other AI systems suggest that they may also be inadequate for achieving socially responsible recommendations. We review how the limitations of human oversight may increase the chances of a specific kind of failure: a "cascade" or "compound" failure. We then briefly explore how the unique dynamics of three common deployment contexts can make humans in the loop more likely to fail in their oversight duties. We then conclude with two recommendations. △ Less

Submitted 25 September, 2025; v1 submitted 24 September, 2025; originally announced September 2025.

DexFruit: Dexterous Manipulation and Gaussian Splatting Inspection of Fruit

Authors: Aiden Swann, Alex Qiu, Matthew Strong, Angelina Zhang, Samuel Morstein, Kai Rayle, Monroe Kennedy III

Abstract: DexFruit is a robotic manipulation framework that enables gentle, autonomous handling of fragile fruit and precise evaluation of damage. Many fruits are fragile and prone to bruising, thus requiring humans to manually harvest them with care. In this work, we demonstrate by using optical tactile sensing, autonomous manipulation of fruit with minimal damage can be achieved. We show that our tactile… ▽ More DexFruit is a robotic manipulation framework that enables gentle, autonomous handling of fragile fruit and precise evaluation of damage. Many fruits are fragile and prone to bruising, thus requiring humans to manually harvest them with care. In this work, we demonstrate by using optical tactile sensing, autonomous manipulation of fruit with minimal damage can be achieved. We show that our tactile informed diffusion policies outperform baselines in both reduced bruising and pick-and-place success rate across three fruits: strawberries, tomatoes, and blackberries. In addition, we introduce FruitSplat, a novel technique to represent and quantify visual damage in high-resolution 3D representation via 3D Gaussian Splatting (3DGS). Existing metrics for measuring damage lack quantitative rigor or require expensive equipment. With FruitSplat, we distill a 2D strawberry mask as well as a 2D bruise segmentation mask into the 3DGS representation. Furthermore, this representation is modular and general, compatible with any relevant 2D model. Overall, we demonstrate a 92% grasping policy success rate, up to a 20% reduction in visual bruising, and up to an 31% improvement in grasp success rate on challenging fruit compared to our baselines across our three tested fruits. We rigorously evaluate this result with over 630 trials. Please checkout our website at https://dex-fruit.github.io . △ Less

Submitted 5 December, 2025; v1 submitted 9 August, 2025; originally announced August 2025.

Comments: 8 pages, 5 figures

TensorTouch: Calibration of Tactile Sensors for High Resolution Stress Tensor and Deformation for Dexterous Manipulation

Authors: Won Kyung Do, Matthew Strong, Aiden Swann, Boshu Lei, Monroe Kennedy III

Abstract: Advanced dexterous manipulation involving multiple simultaneous contacts across different surfaces, like pinching coins from ground or manipulating intertwined objects, remains challenging for robotic systems. Such tasks exceed the capabilities of vision and proprioception alone, requiring high-resolution tactile sensing with calibrated physical metrics. Raw optical tactile sensor images, while in… ▽ More Advanced dexterous manipulation involving multiple simultaneous contacts across different surfaces, like pinching coins from ground or manipulating intertwined objects, remains challenging for robotic systems. Such tasks exceed the capabilities of vision and proprioception alone, requiring high-resolution tactile sensing with calibrated physical metrics. Raw optical tactile sensor images, while information-rich, lack interpretability and cross-sensor transferability, limiting their real-world utility. TensorTouch addresses this challenge by integrating finite element analysis with deep learning to extract comprehensive contact information from optical tactile sensors, including stress tensors, deformation fields, and force distributions at pixel-level resolution. The TensorTouch framework achieves sub-millimeter position accuracy and precise force estimation while supporting large sensor deformations crucial for manipulating soft objects. Experimental validation demonstrates 90% success in selectively grasping one of two strings based on detected motion, enabling new contact-rich manipulation capabilities previously inaccessible to robotic systems. △ Less

Submitted 9 June, 2025; originally announced June 2025.

Diffusion-SAFE: Diffusion-Native Human-to-Robot Driving Handover for Shared Autonomy

Authors: Yunxin Fan, Monroe Kennedy III

Abstract: Shared autonomy in driving requires anticipating human behavior, flagging risk before it becomes unavoidable, and transferring control safely and smoothly. We propose Diffusion-SAFE, a closed-loop framework built on two diffusion models: an evaluator that predicts multimodal human-intent action sequences for probabilistic risk detection, and a safety-guided copilot that steers its denoising proces… ▽ More Shared autonomy in driving requires anticipating human behavior, flagging risk before it becomes unavoidable, and transferring control safely and smoothly. We propose Diffusion-SAFE, a closed-loop framework built on two diffusion models: an evaluator that predicts multimodal human-intent action sequences for probabilistic risk detection, and a safety-guided copilot that steers its denoising process toward safe regions using the gradient of a map-based safety certificate. When risk is detected, control is transferred through partial diffusion: the human plan is forward-noised to an intermediate level and denoised by the safety-guided copilot. The forward-diffusion ratio $ρ$ acts as a continuous takeover knob-small $ρ$ keeps the output close to human intent, while increasing $ρ$ shifts authority toward the copilot, avoiding the mixed-unsafe pitfall of action-level blending. Unlike methods relying on hand-crafted score functions, our diffusion formulation supports both safety evaluation and plan generation directly from demonstrations. We evaluate Diffusion-SAFE in simulation and on a real ROS-based race car, achieving 93.0%/87.0% (sim/real) handover success rates with smooth transitions. △ Less

Submitted 6 March, 2026; v1 submitted 14 May, 2025; originally announced May 2025.

ACM Class: I.2.9; H.5.2

J-PARSE: Jacobian-based Projection Algorithm for Resolving Singularities Effectively in Inverse Kinematic Control of Serial Manipulators

Authors: Shivani Guptasarma, Matthew Strong, Honghao Zhen, Monroe Kennedy III

Abstract: J-PARSE is an algorithm for smooth first-order inverse kinematic control of a serial manipulator near kinematic singularities. The commanded end-effector velocity is interpreted component-wise, according to the available mobility in each dimension of the task space. First, a substitute "Safety" Jacobian matrix is created, keeping the aspect ratio of the manipulability ellipsoid above a threshold v… ▽ More J-PARSE is an algorithm for smooth first-order inverse kinematic control of a serial manipulator near kinematic singularities. The commanded end-effector velocity is interpreted component-wise, according to the available mobility in each dimension of the task space. First, a substitute "Safety" Jacobian matrix is created, keeping the aspect ratio of the manipulability ellipsoid above a threshold value. The desired motion is then projected onto non-singular and singular directions, and the latter projection scaled down by a factor informed by the threshold value. A right-inverse of the non-singular Safety Jacobian is applied to the modified command. In the absence of joint limits and collisions, this ensures safe transition into and out of low-rank configurations, guaranteeing asymptotic stability for reaching target poses within the workspace, and stability for those outside. Velocity control with J-PARSE is benchmarked against approaches from the literature, and shows high accuracy in reaching and leaving singular target poses. By expanding the available workspace of manipulators, the algorithm finds applications in teleoperation, servoing, and learning. Videos and code are available at https://jparse-manip.github.io/. △ Less

Submitted 18 April, 2026; v1 submitted 1 May, 2025; originally announced May 2025.

Comments: 21 pages, 13 figures. v1: Fig. 1 replaced with faster-loading version. v2: Website at https://jparse-manip.github.io/. v3: Proofs revised and new material added. v4: Proofs further revised and more new material added

A Study of Perceived Safety for Soft Robotics in Caregiving Tasks

Authors: Cosima du Pasquier, Jennifer Grannen, Chuer Pan, Serin L. Huber, Aliyah Smith, Monroe Kennedy, Shuran Song, Dorsa Sadigh, Allison M. Okamura

Abstract: In this project, we focus on human-robot interaction in caregiving scenarios like bathing, where physical contact is inevitable and necessary for proper task execution because force must be applied to the skin. Using finite element analysis, we designed a 3D-printed gripper combining positive and negative pressure for secure yet compliant handling. Preliminary tests showed it exerted a lower, more… ▽ More In this project, we focus on human-robot interaction in caregiving scenarios like bathing, where physical contact is inevitable and necessary for proper task execution because force must be applied to the skin. Using finite element analysis, we designed a 3D-printed gripper combining positive and negative pressure for secure yet compliant handling. Preliminary tests showed it exerted a lower, more uniform pressure profile than a standard rigid gripper. In a user study, participants' trust in robots significantly increased after they experienced a brief bathing demonstration performed by a robotic arm equipped with the soft gripper. These results suggest that soft robotics can enhance perceived safety and acceptance in intimate caregiving scenarios. △ Less

Submitted 26 March, 2025; originally announced March 2025.

Through the LLM Looking Glass: A Socratic Probing of Donkeys, Elephants, and Markets

Authors: Molly Kennedy, Ayyoob Imani, Timo Spinde, Akiko Aizawa, Hinrich Schütze

Abstract: Large Language Models (LLMs) are widely used for text generation, making it crucial to address potential bias. This study investigates ideological framing bias in LLM-generated articles, focusing on the subtle and subjective nature of such bias in journalistic contexts. We evaluate eight widely used LLMs on two datasets-POLIGEN and ECONOLEX-covering political and economic discourse where framing b… ▽ More Large Language Models (LLMs) are widely used for text generation, making it crucial to address potential bias. This study investigates ideological framing bias in LLM-generated articles, focusing on the subtle and subjective nature of such bias in journalistic contexts. We evaluate eight widely used LLMs on two datasets-POLIGEN and ECONOLEX-covering political and economic discourse where framing bias is most pronounced. Beyond text generation, LLMs are increasingly used as evaluators (LLM-as-a-judge), providing feedback that can shape human judgment or inform newer model versions. Inspired by the Socratic method, we further analyze LLMs' feedback on their own outputs to identify inconsistencies in their reasoning. Our results show that most LLMs can accurately annotate ideologically framed text, with GPT-4o achieving human-level accuracy and high agreement with human annotators. However, Socratic probing reveals that when confronted with binary comparisons, LLMs often exhibit preference toward one perspective or perceive certain viewpoints as less biased. △ Less

Submitted 12 January, 2026; v1 submitted 20 March, 2025; originally announced March 2025.

Localization of Vibrotactile Stimuli on the Face

Authors: Shivani Guptasarma, Allison M. Okamura, Monroe Kennedy III

Abstract: The face remains relatively unexplored as a target region for haptic feedback, despite providing a considerable surface area consisting of highly sensitive skin. There are promising applications for facial haptic feedback, especially in cases of severe upper limb loss or spinal cord injury, where the face is typically less impacted than other body parts. Moreover, the neural representation of the… ▽ More The face remains relatively unexplored as a target region for haptic feedback, despite providing a considerable surface area consisting of highly sensitive skin. There are promising applications for facial haptic feedback, especially in cases of severe upper limb loss or spinal cord injury, where the face is typically less impacted than other body parts. Moreover, the neural representation of the face is adjacent to that of the hand, and phantom maps have been discovered between the fingertips and the cheeks. However, there is a dearth of compact devices for facial haptic feedback, and vibrotactile stimulation, a common modality of haptic feedback, has not been characterized for localization acuity on the face. We performed a localization experiment on the cheek, with an arrangement of off-the-shelf coin vibration motors. The study follows the methods of prior work studying other skin regions, in which participants attempt to identify the sites of discrete vibrotactile stimuli. We intend for our results to inform the future development of systems using vibrotactile feedback to convey information via the face. △ Less

Submitted 6 February, 2025; originally announced February 2025.

Comments: 5 pages, 5 figures

Vernacularizing Taxonomies of Harm is Essential for Operationalizing Holistic AI Safety

Authors: Wm. Matthew Kennedy, Daniel Vargas Campos

Abstract: Operationalizing AI ethics and safety principles and frameworks is essential to realizing the potential benefits and mitigating potential harms caused by AI systems. To that end, actors across industry, academia, and regulatory bodies have created formal taxonomies of harm to support operationalization efforts. These include novel holistic methods that go beyond exclusive reliance on technical ben… ▽ More Operationalizing AI ethics and safety principles and frameworks is essential to realizing the potential benefits and mitigating potential harms caused by AI systems. To that end, actors across industry, academia, and regulatory bodies have created formal taxonomies of harm to support operationalization efforts. These include novel holistic methods that go beyond exclusive reliance on technical benchmarking. However, our paper argues that such taxonomies must also be transferred into local categories to be readily implemented in sector-specific AI safety operationalization efforts, and especially in underresourced or high-risk sectors. This is because many sectors are constituted by discourses, norms, and values that "refract" or even directly conflict with those operating in society more broadly. Drawing from emerging anthropological theories of human rights, we propose that the process of "vernacularization"--a participatory, decolonial practice distinct from doctrinary "translation" (the dominant mode of AI safety operationalization)--can help bridge this gap. To demonstrate this point, we consider the education sector, and identify precisely how vernacularizing a leading holistic taxonomy of harm leads to a clearer view of how harms AI systems may cause are substantially intensified when deployed in educational spaces. We conclude by discussing the generalizability of vernacularization as a useful AI safety methodology. △ Less

Submitted 21 October, 2024; originally announced October 2024.

Comments: Accepted to the Proceedings of the Conference on AI Ethics and Society (AIES), 2024

Understanding and Imitating Human-Robot Motion with Restricted Visual Fields

Authors: Maulik Bhatt, HongHao Zhen, Monroe Kennedy III, Negar Mehr

Abstract: When working around other agents such as humans, it is important to model their perception capabilities to predict and make sense of their behavior. In this work, we consider agents whose perception capabilities are determined by their limited field of view, viewing range, and the potential to miss objects within their viewing range. By considering the perception capabilities and observation model… ▽ More When working around other agents such as humans, it is important to model their perception capabilities to predict and make sense of their behavior. In this work, we consider agents whose perception capabilities are determined by their limited field of view, viewing range, and the potential to miss objects within their viewing range. By considering the perception capabilities and observation model of agents independently from their motion policy, we show that we can better predict the agents' behavior; i.e., by reasoning about the perception capabilities of other agents, one can better make sense of their actions. We perform a user study where human operators navigate a cluttered scene while scanning the region for obstacles with a limited field of view and range. We show that by reasoning about the limited observation space of humans, a robot can better learn a human's strategy for navigating an environment and navigate with minimal collision with dynamic and static obstacles. We also show that this learned model helps it successfully navigate a physical hardware vehicle in real-time. Code available at https://github.com/labicon/HRMotion-RestrictedView. △ Less

Submitted 9 August, 2025; v1 submitted 7 October, 2024; originally announced October 2024.

Next Best Sense: Guiding Vision and Touch with FisherRF for 3D Gaussian Splatting

Authors: Matthew Strong, Boshu Lei, Aiden Swann, Wen Jiang, Kostas Daniilidis, Monroe Kennedy III

Abstract: We propose a framework for active next best view and touch selection for robotic manipulators using 3D Gaussian Splatting (3DGS). 3DGS is emerging as a useful explicit 3D scene representation for robotics, as it has the ability to represent scenes in a both photorealistic and geometrically accurate manner. However, in real-world, online robotic scenes where the number of views is limited given eff… ▽ More We propose a framework for active next best view and touch selection for robotic manipulators using 3D Gaussian Splatting (3DGS). 3DGS is emerging as a useful explicit 3D scene representation for robotics, as it has the ability to represent scenes in a both photorealistic and geometrically accurate manner. However, in real-world, online robotic scenes where the number of views is limited given efficiency requirements, random view selection for 3DGS becomes impractical as views are often overlapping and redundant. We address this issue by proposing an end-to-end online training and active view selection pipeline, which enhances the performance of 3DGS in few-view robotics settings. We first elevate the performance of few-shot 3DGS with a novel semantic depth alignment method using Segment Anything Model 2 (SAM2) that we supplement with Pearson depth and surface normal loss to improve color and depth reconstruction of real-world scenes. We then extend FisherRF, a next-best-view selection method for 3DGS, to select views and touch poses based on depth uncertainty. We perform online view selection on a real robot system during live 3DGS training. We motivate our improvements to few-shot GS scenes, and extend depth-based FisherRF to them, where we demonstrate both qualitative and quantitative improvements on challenging robot scenes. For more information, please see our project page at https://arm.stanford.edu/next-best-sense. △ Less

Submitted 8 March, 2025; v1 submitted 6 October, 2024; originally announced October 2024.

Comments: To appear in International Conference on Robotics and Automation (ICRA) 2025

Towards Accessible Robot Control: Comparing Kinesthetic Teaching, SpaceMouse Teleoperation, and a Mixed Reality Interface

Authors: Aliyah Smith, Monroe Kennedy III

Abstract: Teleoperation interfaces are essential tools for enabling human control of robotic systems. Although a wide range of interfaces has been developed, a persistent gap remains between the level of performance humans can achieve through these interfaces and the capabilities afforded by direct human-guided robot control. This gap is further exacerbated when users are inexperienced or unfamiliar with th… ▽ More Teleoperation interfaces are essential tools for enabling human control of robotic systems. Although a wide range of interfaces has been developed, a persistent gap remains between the level of performance humans can achieve through these interfaces and the capabilities afforded by direct human-guided robot control. This gap is further exacerbated when users are inexperienced or unfamiliar with the robotic platform or control interface. In this work, we aim to better characterize this performance gap for non-expert users by comparing two teleoperation approaches, SpaceMouse teleoperation and a Mixed Reality (MR) interface, against kinesthetic teaching as a non-teleoperation baseline. All three approaches were evaluated in a comprehensive user study involving two robotic platforms and six complex manipulation tasks. Quantitative results show that the SpaceMouse and MR interfaces performed comparably, with significant differences in task completion observed for only two tasks, and success rates declining as task complexity increased. Qualitative analysis reflected these trends, highlighting differences in Physical Demand and identifying interface attributes that influence users' ability to perform, learn, and understand. This study quantifies the limitations of current teleoperation methods and incorporates subjective feedback from 25 participants. The results highlight the critical need to design and rigorously evaluate teleoperation systems for non-expert users, particularly in contexts where autonomous robots are deployed in personal or everyday environments, to ensure usability, efficiency, and accessibility. △ Less

Submitted 16 January, 2026; v1 submitted 26 September, 2024; originally announced September 2024.

Comments: 32 pages, 12 figures

SAFER-Splat: A Control Barrier Function for Safe Navigation with Online Gaussian Splatting Maps

Authors: Timothy Chen, Aiden Swann, Javier Yu, Ola Shorinwa, Riku Murai, Monroe Kennedy III, Mac Schwager

Abstract: SAFER-Splat (Simultaneous Action Filtering and Environment Reconstruction) is a real-time, scalable, and minimally invasive action filter, based on control barrier functions, for safe robotic navigation in a detailed map constructed at runtime using Gaussian Splatting (GSplat). We propose a novel Control Barrier Function (CBF) that not only induces safety with respect to all Gaussian primitives in… ▽ More SAFER-Splat (Simultaneous Action Filtering and Environment Reconstruction) is a real-time, scalable, and minimally invasive action filter, based on control barrier functions, for safe robotic navigation in a detailed map constructed at runtime using Gaussian Splatting (GSplat). We propose a novel Control Barrier Function (CBF) that not only induces safety with respect to all Gaussian primitives in the scene, but when synthesized into a controller, is capable of processing hundreds of thousands of Gaussians while maintaining a minimal memory footprint and operating at 15 Hz during online Splat training. Of the total compute time, a small fraction of it consumes GPU resources, enabling uninterrupted training. The safety layer is minimally invasive, correcting robot actions only when they are unsafe. To showcase the safety filter, we also introduce SplatBridge, an open-source software package built with ROS for real-time GSplat mapping for robots. We demonstrate the safety and robustness of our pipeline first in simulation, where our method is 20-50x faster, safer, and less conservative than competing methods based on neural radiance fields. Further, we demonstrate simultaneous GSplat mapping and safety filtering on a drone hardware platform using only on-board perception. We verify that under teleoperation a human pilot cannot invoke a collision. Our videos and codebase can be found at https://chengine.github.io/safer-splat. △ Less

Submitted 17 March, 2025; v1 submitted 15 September, 2024; originally announced September 2024.

Comments: Accepted to International Conference on Robotics and Automation

Dynamic Layer Detection of Thin Materials using DenseTact Optical Tactile Sensors

Authors: Ankush Kundan Dhawan, Camille Chungyoun, Karina Ting, Monroe Kennedy III

Abstract: Manipulation of thin materials is critical for many everyday tasks and remains a significant challenge for robots. While existing research has made strides in tasks like material smoothing and folding, many studies struggle with common failure modes (crumpled corners/edges, incorrect grasp configurations) that a preliminary step of layer detection could solve. We present a novel method for classif… ▽ More Manipulation of thin materials is critical for many everyday tasks and remains a significant challenge for robots. While existing research has made strides in tasks like material smoothing and folding, many studies struggle with common failure modes (crumpled corners/edges, incorrect grasp configurations) that a preliminary step of layer detection could solve. We present a novel method for classifying the number of grasped material layers using a custom gripper equipped with DenseTact 2.0 optical tactile sensors. After grasping, the gripper performs an anthropomorphic rubbing motion while collecting optical flow, 6-axis wrench, and joint state data. Using this data in a transformer-based network achieves a test accuracy of 98.21\% in classifying the number of grasped cloth layers, and 81.25\% accuracy in classifying layers of grasped paper, showing the effectiveness of our dynamic rubbing method. Evaluating different inputs and model architectures highlights the usefulness of tactile sensor information and a transformer model for this task. A comprehensive dataset of 568 labeled trials (368 for cloth and 200 for paper) was collected and made open-source along with this paper. Our project page is available at https://armlabstanford.github.io/dynamic-cloth-detection. △ Less

Submitted 11 August, 2025; v1 submitted 15 September, 2024; originally announced September 2024.

Comments: 7 pages, 9 figures, accepted to IROS 2025

ProACT: An Augmented Reality Testbed for Intelligent Prosthetic Arms

Authors: Shivani Guptasarma, Monroe D. Kennedy III

Abstract: Upper-limb amputees face tremendous difficulty in operating dexterous powered prostheses. Previous work has shown that aspects of prosthetic hand, wrist, or elbow control can be improved through "intelligent" control, by combining movement-based or gaze-based intent estimation with low-level robotic autonomy. However, no such solutions exist for whole-arm control. Moreover, hardware platforms for… ▽ More Upper-limb amputees face tremendous difficulty in operating dexterous powered prostheses. Previous work has shown that aspects of prosthetic hand, wrist, or elbow control can be improved through "intelligent" control, by combining movement-based or gaze-based intent estimation with low-level robotic autonomy. However, no such solutions exist for whole-arm control. Moreover, hardware platforms for advanced prosthetic control are expensive, and existing simulation platforms are not well-designed for integration with robotics software frameworks. We present the Prosthetic Arm Control Testbed (ProACT), a platform for evaluating intelligent control methods for prosthetic arms in an immersive (Augmented Reality) simulation setting. We demonstrate the use of ProACT through preliminary studies, with non-amputee participants performing an adapted Box-and-Blocks task with and without intent estimation. We further discuss how our observations may inform the design of prosthesis control methods, as well as the design of future studies using the platform. To the best of our knowledge, this constitutes the first study of semi-autonomous control for complex whole-arm prostheses, the first study including sequential task modeling in the context of wearable prosthetic arms, and the first testbed of its kind. Towards the goal of supporting future research in intelligent prosthetics, the system is built upon on existing open-source frameworks for robotics, and is available at https://arm.stanford.edu/proact. △ Less

Submitted 2 December, 2024; v1 submitted 6 July, 2024; originally announced July 2024.

Comments: 12 pages, 8 figures. Under review. Code and data are available at https://arm.stanford.edu/proact

Journal ref: IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 33, pp. 354-365, 2025

Splat-MOVER: Multi-Stage, Open-Vocabulary Robotic Manipulation via Editable Gaussian Splatting

Authors: Ola Shorinwa, Johnathan Tucker, Aliyah Smith, Aiden Swann, Timothy Chen, Roya Firoozi, Monroe Kennedy III, Mac Schwager

Abstract: We present Splat-MOVER, a modular robotics stack for open-vocabulary robotic manipulation, which leverages the editability of Gaussian Splatting (GSplat) scene representations to enable multi-stage manipulation tasks. Splat-MOVER consists of: (i) ASK-Splat, a GSplat representation that distills semantic and grasp affordance features into the 3D scene. ASK-Splat enables geometric, semantic, and aff… ▽ More We present Splat-MOVER, a modular robotics stack for open-vocabulary robotic manipulation, which leverages the editability of Gaussian Splatting (GSplat) scene representations to enable multi-stage manipulation tasks. Splat-MOVER consists of: (i) ASK-Splat, a GSplat representation that distills semantic and grasp affordance features into the 3D scene. ASK-Splat enables geometric, semantic, and affordance understanding of 3D scenes, which is critical in many robotics tasks; (ii) SEE-Splat, a real-time scene-editing module using 3D semantic masking and infilling to visualize the motions of objects that result from robot interactions in the real-world. SEE-Splat creates a "digital twin" of the evolving environment throughout the manipulation task; and (iii) Grasp-Splat, a grasp generation module that uses ASK-Splat and SEE-Splat to propose affordance-aligned candidate grasps for open-world objects. ASK-Splat is trained in real-time from RGB images in a brief scanning phase prior to operation, while SEE-Splat and Grasp-Splat run in real-time during operation. We demonstrate the superior performance of Splat-MOVER in hardware experiments on a Kinova robot compared to two recent baselines in four single-stage, open-vocabulary manipulation tasks and in four multi-stage manipulation tasks, using the edited scene to reflect changes due to prior manipulation stages, which is not possible with existing baselines. Video demonstrations and the code for the project are available at https://splatmover.github.io. △ Less

Submitted 26 September, 2024; v1 submitted 7 May, 2024; originally announced May 2024.

Comments: https://splatmover.github.io

EgoNav: Egocentric Scene-aware Human Trajectory Prediction

Authors: Weizhuo Wang, C. Karen Liu, Monroe Kennedy III

Abstract: Wearable collaborative robots stand to assist human wearers who need fall prevention assistance or wear exoskeletons. Such a robot needs to be able to constantly adapt to the surrounding scene based on egocentric vision, and predict the ego motion of the wearer. In this work, we leveraged body-mounted cameras and sensors to anticipate the trajectory of human wearers through complex surroundings. T… ▽ More Wearable collaborative robots stand to assist human wearers who need fall prevention assistance or wear exoskeletons. Such a robot needs to be able to constantly adapt to the surrounding scene based on egocentric vision, and predict the ego motion of the wearer. In this work, we leveraged body-mounted cameras and sensors to anticipate the trajectory of human wearers through complex surroundings. To facilitate research in ego-motion prediction, we have collected a comprehensive walking scene navigation dataset centered on the user's perspective. We then present a method to predict human motion conditioning on the surrounding static scene. Our method leverages a diffusion model to produce a distribution of potential future trajectories, taking into account the user's observation of the environment. To that end, we introduce a compact representation to encode the user's visual memory of the surroundings, as well as an efficient sample-generating technique to speed up real-time inference of a diffusion model. We ablate our model and compare it to baselines, and results show that our model outperforms existing methods on key metrics of collision avoidance and trajectory mode coverage. △ Less

Submitted 7 August, 2024; v1 submitted 27 March, 2024; originally announced March 2024.

Comments: 13 pages, 9 figures

Touch-GS: Visual-Tactile Supervised 3D Gaussian Splatting

Authors: Aiden Swann, Matthew Strong, Won Kyung Do, Gadiel Sznaier Camps, Mac Schwager, Monroe Kennedy III

Abstract: In this work, we propose a novel method to supervise 3D Gaussian Splatting (3DGS) scenes using optical tactile sensors. Optical tactile sensors have become widespread in their use in robotics for manipulation and object representation; however, raw optical tactile sensor data is unsuitable to directly supervise a 3DGS scene. Our representation leverages a Gaussian Process Implicit Surface to impli… ▽ More In this work, we propose a novel method to supervise 3D Gaussian Splatting (3DGS) scenes using optical tactile sensors. Optical tactile sensors have become widespread in their use in robotics for manipulation and object representation; however, raw optical tactile sensor data is unsuitable to directly supervise a 3DGS scene. Our representation leverages a Gaussian Process Implicit Surface to implicitly represent the object, combining many touches into a unified representation with uncertainty. We merge this model with a monocular depth estimation network, which is aligned in a two stage process, coarsely aligning with a depth camera and then finely adjusting to match our touch data. For every training image, our method produces a corresponding fused depth and uncertainty map. Utilizing this additional information, we propose a new loss function, variance weighted depth supervised loss, for training the 3DGS scene model. We leverage the DenseTact optical tactile sensor and RealSense RGB-D camera to show that combining touch and vision in this manner leads to quantitatively and qualitatively better results than vision or touch alone in a few-view scene syntheses on opaque as well as on reflective and transparent objects. Please see our project page at http://armlabstanford.github.io/touch-gs △ Less

Submitted 15 August, 2024; v1 submitted 14 March, 2024; originally announced March 2024.

Comments: 8 pages, 7 figures

Considerations for the Control Design of Augmentative Robots

Authors: Shivani Guptasarma, Monroe Kennedy III

Abstract: Robotic systems that are intended to augment human capabilities commonly require the use of semi-autonomous control and artificial sensing, while at the same time aiming to empower the user to make decisions and take actions. This work identifies principles and techniques from the literature that can help to resolve this apparent contradiction. It is postulated that augmentative robots must functi… ▽ More Robotic systems that are intended to augment human capabilities commonly require the use of semi-autonomous control and artificial sensing, while at the same time aiming to empower the user to make decisions and take actions. This work identifies principles and techniques from the literature that can help to resolve this apparent contradiction. It is postulated that augmentative robots must function as tools that have partial agency, as collaborative agents that provide conditional transparency, and ideally, serve as extensions of the human body. △ Less

Submitted 31 October, 2023; v1 submitted 30 October, 2023; originally announced October 2023.

Comments: 7 pages. Presented at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021) Workshop on Building and Evaluating Ethical Robotic Systems, Prague, Czech Republic, 28-30 September 2021

Evaluating Adversarial Robustness with Expected Viable Performance

Authors: Ryan McCoppin, Colin Dawson, Sean M. Kennedy, Leslie M. Blaha

Abstract: We introduce a metric for evaluating the robustness of a classifier, with particular attention to adversarial perturbations, in terms of expected functionality with respect to possible adversarial perturbations. A classifier is assumed to be non-functional (that is, has a functionality of zero) with respect to a perturbation bound if a conventional measure of performance, such as classification ac… ▽ More We introduce a metric for evaluating the robustness of a classifier, with particular attention to adversarial perturbations, in terms of expected functionality with respect to possible adversarial perturbations. A classifier is assumed to be non-functional (that is, has a functionality of zero) with respect to a perturbation bound if a conventional measure of performance, such as classification accuracy, is less than a minimally viable threshold when the classifier is tested on examples from that perturbation bound. Defining robustness in terms of an expected value is motivated by a domain general approach to robustness quantification. △ Less

Submitted 18 September, 2023; originally announced September 2023.

Comments: Accepted at the 22nd International Conference on Machine Learning and Applications (IEEE 2023)

DenseTact-Mini: An Optical Tactile Sensor for Grasping Multi-Scale Objects From Flat Surfaces

Authors: Won Kyung Do, Ankush Kundan Dhawan, Mathilda Kitzmann, Monroe Kennedy III

Abstract: Dexterous manipulation, especially of small daily objects, continues to pose complex challenges in robotics. This paper introduces the DenseTact-Mini, an optical tactile sensor with a soft, rounded, smooth gel surface and compact design equipped with a synthetic fingernail. We propose three distinct grasping strategies: tap grasping using adhesion forces such as electrostatic and van der Waals, fi… ▽ More Dexterous manipulation, especially of small daily objects, continues to pose complex challenges in robotics. This paper introduces the DenseTact-Mini, an optical tactile sensor with a soft, rounded, smooth gel surface and compact design equipped with a synthetic fingernail. We propose three distinct grasping strategies: tap grasping using adhesion forces such as electrostatic and van der Waals, fingernail grasping leveraging rolling/sliding contact between the object and fingernail, and fingertip grasping with two soft fingertips. Through comprehensive evaluations, the DenseTact-Mini demonstrates a lifting success rate exceeding 90.2% when grasping various objects, spanning items from 1mm basil seeds and small paperclips to items nearly 15mm. This work demonstrates the potential of soft optical tactile sensors for dexterous manipulation and grasping. △ Less

Submitted 15 September, 2023; originally announced September 2023.

Inter-finger Small Object Manipulation with DenseTact Optical Tactile Sensor

Authors: Won Kyung Do, Bianca Aumann, Camille Chungyoun, Monroe Kennedy III

Abstract: The ability to grasp and manipulate small objects in cluttered environments remains a significant challenge. This paper introduces a novel approach that utilizes a tactile sensor-equipped gripper with eight degrees of freedom to overcome these limitations. We employ DenseTact 2.0 for the gripper, enabling precise control and improved grasp success rates, particularly for small objects ranging from… ▽ More The ability to grasp and manipulate small objects in cluttered environments remains a significant challenge. This paper introduces a novel approach that utilizes a tactile sensor-equipped gripper with eight degrees of freedom to overcome these limitations. We employ DenseTact 2.0 for the gripper, enabling precise control and improved grasp success rates, particularly for small objects ranging from 5mm to 25mm. Our integrated strategy incorporates the robot arm, gripper, and sensor to manipulate and orient small objects for subsequent classification effectively. We contribute a specialized dataset designed for classifying these objects based on tactile sensor output and a new control algorithm for in-hand orientation tasks. Our system demonstrates 88% of successful grasp and successfully classified small objects in cluttered scenarios. △ Less

Submitted 31 August, 2023; originally announced August 2023.

Embedded Object Detection and Mapping in Soft Materials Using Optical Tactile Sensing

Authors: Jose A. Solano-Castellanos, Won Kyung Do, Monroe Kennedy III

Abstract: In this paper, we present a methodology that uses an optical tactile sensor for efficient tactile exploration of embedded objects within soft materials. The methodology consists of an exploration phase, where a probabilistic estimate of the location of the embedded objects is built using a Bayesian approach. The exploration phase is then followed by a mapping phase which exploits the probabilistic… ▽ More In this paper, we present a methodology that uses an optical tactile sensor for efficient tactile exploration of embedded objects within soft materials. The methodology consists of an exploration phase, where a probabilistic estimate of the location of the embedded objects is built using a Bayesian approach. The exploration phase is then followed by a mapping phase which exploits the probabilistic map to reconstruct the underlying topography of the workspace by sampling in more detail regions where there is expected to be embedded objects. To demonstrate the effectiveness of the method, we tested our approach on an experimental setup that consists of a series of quartz beads located underneath a polyethylene foam that prevents direct observation of the configuration and requires the use of tactile exploration to recover the location of the beads. We show the performance of our methodology using ten different configurations of the beads where the proposed approach is able to approximate the underlying configuration. We benchmark our results against a random sampling policy. △ Less

Submitted 21 August, 2023; originally announced August 2023.

Journal ref: Springer Nature Computer Science, Vol 5, Article 372, 2024

Overcoming Adversarial Attacks for Human-in-the-Loop Applications

Authors: Ryan McCoppin, Marla Kennedy, Platon Lukyanenko, Sean Kennedy

Abstract: Including human analysis has the potential to positively affect the robustness of Deep Neural Networks and is relatively unexplored in the Adversarial Machine Learning literature. Neural network visual explanation maps have been shown to be prone to adversarial attacks. Further research is needed in order to select robust visualizations of explanations for the image analyst to evaluate a given mod… ▽ More Including human analysis has the potential to positively affect the robustness of Deep Neural Networks and is relatively unexplored in the Adversarial Machine Learning literature. Neural network visual explanation maps have been shown to be prone to adversarial attacks. Further research is needed in order to select robust visualizations of explanations for the image analyst to evaluate a given model. These factors greatly impact Human-In-The-Loop (HITL) evaluation tools due to their reliance on adversarial images, including explanation maps and measurements of robustness. We believe models of human visual attention may improve interpretability and robustness of human-machine imagery analysis systems. Our challenge remains, how can HITL evaluation be robust in this adversarial landscape? △ Less

Submitted 25 August, 2023; v1 submitted 9 June, 2023; originally announced June 2023.

Comments: New Frontiers in Adversarial Machine Learning, ICML 2022

Diffusion Co-Policy for Synergistic Human-Robot Collaborative Tasks

Authors: Eley Ng, Ziang Liu, Monroe Kennedy III

Abstract: Modeling multimodal human behavior has been a key barrier to increasing the level of interaction between human and robot, particularly for collaborative tasks. Our key insight is that an effective, learned robot policy used for human-robot collaborative tasks must be able to express a high degree of multimodality, predict actions in a temporally consistent manner, and recognize a wide range of fre… ▽ More Modeling multimodal human behavior has been a key barrier to increasing the level of interaction between human and robot, particularly for collaborative tasks. Our key insight is that an effective, learned robot policy used for human-robot collaborative tasks must be able to express a high degree of multimodality, predict actions in a temporally consistent manner, and recognize a wide range of frequencies of human actions in order to seamlessly integrate with a human in the control loop. We present Diffusion Co-policy, a method for planning sequences of actions that synergize well with humans during test time. The co-policy predicts joint human-robot action sequences via a Transformer-based diffusion model, which is trained on a dataset of collaborative human-human demonstrations, and directly executes the robot actions in a receding horizon control framework. We demonstrate in both simulation and real environments that the method outperforms other state-of-art learning methods on the task of human-robot table-carrying with a human in the loop. Moreover, we qualitatively highlight compelling robot behaviors that demonstrate evidence of true human-robot collaboration, including mutual adaptation, shared task understanding, leadership switching, and low levels of wasteful interaction forces arising from dissent. △ Less

Submitted 12 November, 2023; v1 submitted 20 May, 2023; originally announced May 2023.

Comments: IEEE Robotics and Automation Letters (RA-L), 2023. 8 pages, 7 figures, 3 tables. Supplementary material at https://sites.google.com/view/diffusion-co-policy-hrc

The Participation Game

Authors: Mark Thomas Kennedy, Nelson Phillips

Abstract: Inspired by Turing's famous "imitation game" and recent advances in generative pre-trained transformers, we pose the participation game to point to a new frontier in AI evolution where machines will join with humans as participants in social construction processes. The participation game is a creative, playful competition that calls for applying, bending, and stretching the categories humans use t… ▽ More Inspired by Turing's famous "imitation game" and recent advances in generative pre-trained transformers, we pose the participation game to point to a new frontier in AI evolution where machines will join with humans as participants in social construction processes. The participation game is a creative, playful competition that calls for applying, bending, and stretching the categories humans use to make sense of and order their worlds. After defining the game and giving reasons for moving beyond imitation as a test of AI, we highlight parallels between the participation game and processes of social construction, a hallmark of human intelligence. We then discuss implications for fundamental constructs of societies and options for governance. △ Less

Submitted 25 April, 2023; originally announced April 2023.

Innovation-Based Remote State Estimation Secrecy with no Acknowledgments

Authors: Justin M. Kennedy, Jason J. Ford, Daniel E. Quevedo, Falko Dressler

Abstract: Secrecy encoding for remote state estimation in the presence of adversarial eavesdroppers is a well studied problem. Typical existing secrecy encoding schemes rely on the transmitter's knowledge of the remote estimator's current performance. This performance measure is often shared via packet receipt acknowledgments. However, in practical situations the acknowledgment channel may be susceptible to… ▽ More Secrecy encoding for remote state estimation in the presence of adversarial eavesdroppers is a well studied problem. Typical existing secrecy encoding schemes rely on the transmitter's knowledge of the remote estimator's current performance. This performance measure is often shared via packet receipt acknowledgments. However, in practical situations the acknowledgment channel may be susceptible to interference from an active adversary, resulting in the secrecy encoding scheme failing. Aiming to achieve a reliable state estimate for a legitimate estimator while ensuring secrecy, we propose a secrecy encoding scheme without the need for packet receipt acknowledgments. Our encoding scheme uses a pre-arranged scheduling sequence established at the transmitter and legitimate receiver. We transmit a packet containing either the state measurement or encoded information for the legitimate user. The encoding makes the packet appear to be the state but is designed to damage an eavesdropper's estimate. The pre-arranged scheduling sequence and encoding is chosen psuedo-random. We analyze the performance of our encoding scheme against a class of eavesdropper, and show conditions to force the eavesdropper to have an unbounded estimation performance. Further, we provide a numerical illustration and apply our encoding scheme to an application in power systems. △ Less

Submitted 15 December, 2022; originally announced December 2022.

Comments: 21 pages, 5 figures

Journal ref: IEEE Transactions on Automatic Control, 2024

It Takes Two: Learning to Plan for Human-Robot Cooperative Carrying

Authors: Eley Ng, Ziang Liu, Monroe Kennedy III

Abstract: Cooperative table-carrying is a complex task due to the continuous nature of the action and state-spaces, multimodality of strategies, and the need for instantaneous adaptation to other agents. In this work, we present a method for predicting realistic motion plans for cooperative human-robot teams on the task. Using a Variational Recurrent Neural Network (VRNN) to model the variation in the traje… ▽ More Cooperative table-carrying is a complex task due to the continuous nature of the action and state-spaces, multimodality of strategies, and the need for instantaneous adaptation to other agents. In this work, we present a method for predicting realistic motion plans for cooperative human-robot teams on the task. Using a Variational Recurrent Neural Network (VRNN) to model the variation in the trajectory of a human-robot team across time, we are able to capture the distribution over the team's future states while leveraging information from interaction history. The key to our approach is leveraging human demonstration data to generate trajectories that synergize well with humans during test time in a receding horizon fashion. Comparison between a baseline, sampling-based planner RRT (Rapidly-exploring Random Trees) and the VRNN planner in centralized planning shows that the VRNN generates motion more similar to the distribution of human-human demonstrations than the RRT. Results in a human-in-the-loop user study show that the VRNN planner outperforms decentralized RRT on task-related metrics, and is significantly more likely to be perceived as human than the RRT planner. Finally, we demonstrate the VRNN planner on a real robot paired with a human teleoperating another robot. △ Less

Submitted 7 March, 2023; v1 submitted 26 September, 2022; originally announced September 2022.

Comments: IEEE International Conference on Robotics and Automation (ICRA) 2023. Supplementary materials at https://sites.google.com/view/cooperative-carrying

Trajectory and Sway Prediction Towards Fall Prevention

Authors: Weizhuo Wang, Michael Raitor, Steve Collins, C. Karen Liu, Monroe Kennedy III

Abstract: Falls are the leading cause of fatal and non-fatal injuries, particularly for older persons. Imbalance can result from the body's internal causes (illness), or external causes (active or passive perturbation). Active perturbation results from applying an external force to a person, while passive perturbation results from human motion interacting with a static obstacle. This work proposes a metric… ▽ More Falls are the leading cause of fatal and non-fatal injuries, particularly for older persons. Imbalance can result from the body's internal causes (illness), or external causes (active or passive perturbation). Active perturbation results from applying an external force to a person, while passive perturbation results from human motion interacting with a static obstacle. This work proposes a metric that allows for the monitoring of the person's torso and its correlation to active and passive perturbations. We show that large changes in the torso sway can be strongly correlated to active perturbations. We also show that we can reasonably predict the future path and expected change in torso sway by conditioning the expected path and torso sway on the past trajectory, torso motion, and the surrounding scene. This could have direct future applications to fall prevention. Results demonstrate that the torso sway is strongly correlated with perturbations. And our model is able to make use of the visual cues presented in the panorama and condition the prediction accordingly. △ Less

Submitted 3 March, 2023; v1 submitted 23 September, 2022; originally announced September 2022.

Comments: 6 pages + 1 page reference, 11 figures. Accepted by ICRA 2023

DenseTact 2.0: Optical Tactile Sensor for Shape and Force Reconstruction

Authors: Won Kyung Do, Bianca Jurewicz, Monroe Kennedy III

Abstract: Collaborative robots stand to have an immense impact on both human welfare in domestic service applications and industrial superiority in advanced manufacturing with dexterous assembly. The outstanding challenge is providing robotic fingertips with a physical design that makes them adept at performing dexterous tasks that require high-resolution, calibrated shape reconstruction and force sensing.… ▽ More Collaborative robots stand to have an immense impact on both human welfare in domestic service applications and industrial superiority in advanced manufacturing with dexterous assembly. The outstanding challenge is providing robotic fingertips with a physical design that makes them adept at performing dexterous tasks that require high-resolution, calibrated shape reconstruction and force sensing. In this work, we present DenseTact 2.0, an optical-tactile sensor capable of visualizing the deformed surface of a soft fingertip and using that image in a neural network to perform both calibrated shape reconstruction and 6-axis wrench estimation. We demonstrate the sensor accuracy of 0.3633mm per pixel for shape reconstruction, 0.410N for forces, 0.387Nmm for torques, and the ability to calibrate new fingers through transfer learning, which achieves comparable performance with only 12% of the non-transfer learning dataset size. △ Less

Submitted 4 March, 2023; v1 submitted 21 September, 2022; originally announced September 2022.

Self-Supervised Clustering on Image-Subtracted Data with Deep-Embedded Self-Organizing Map

Authors: Y. -L. Mong, K. Ackley, T. L. Killestein, D. K. Galloway, M. Dyer, R. Cutter, M. J. I. Brown, J. Lyman, K. Ulaczyk, D. Steeghs, V. Dhillon, P. O'Brien, G. Ramsay, K. Noysena, R. Kotak, R. Breton, L. Nuttall, E. Palle, D. Pollacco, E. Thrane, S. Awiphan, U. Burhanudin, P. Chote, A. Chrimes, E. Daw , et al. (23 additional authors not shown)

Abstract: Developing an effective automatic classifier to separate genuine sources from artifacts is essential for transient follow-ups in wide-field optical surveys. The identification of transient detections from the subtraction artifacts after the image differencing process is a key step in such classifiers, known as real-bogus classification problem. We apply a self-supervised machine learning model, th… ▽ More Developing an effective automatic classifier to separate genuine sources from artifacts is essential for transient follow-ups in wide-field optical surveys. The identification of transient detections from the subtraction artifacts after the image differencing process is a key step in such classifiers, known as real-bogus classification problem. We apply a self-supervised machine learning model, the deep-embedded self-organizing map (DESOM) to this "real-bogus" classification problem. DESOM combines an autoencoder and a self-organizing map to perform clustering in order to distinguish between real and bogus detections, based on their dimensionality-reduced representations. We use 32x32 normalized detection thumbnails as the input of DESOM. We demonstrate different model training approaches, and find that our best DESOM classifier shows a missed detection rate of 6.6% with a false positive rate of 1.5%. DESOM offers a more nuanced way to fine-tune the decision boundary identifying likely real detections when used in combination with other types of classifiers, for example built on neural networks or decision trees. We also discuss other potential usages of DESOM and its limitations. △ Less

Submitted 13 September, 2022; originally announced September 2022.

Playing catch-up in building an open research commons

Authors: Philip E. Bourne, Vivien Bonazzi, Amy Brand, Bonnie Carroll, Ian Foster, Ramanathan V. Guha, Robert Hanisch, Sallie Ann Keller, Mary Lee Kennedy, Christine Kirkpatrick, Barend Mons, Sarah M. Nusser, Michael Stebbins, George Strawn, Alex Szalay

Abstract: On August 2, 2021 a group of concerned scientists and US funding agency and federal government officials met for an informal discussion to explore the value and need for a well-coordinated US Open Research Commons (ORC); an interoperable collection of data and compute resources within both the public and private sectors which are easy to use and accessible to all. On August 2, 2021 a group of concerned scientists and US funding agency and federal government officials met for an informal discussion to explore the value and need for a well-coordinated US Open Research Commons (ORC); an interoperable collection of data and compute resources within both the public and private sectors which are easy to use and accessible to all. △ Less

Submitted 15 July, 2022; originally announced August 2022.

Comments: 3 pages on the AAS template

A Modified PINN Approach for Identifiable Compartmental Models in Epidemiology with Applications to COVID-19

Authors: Haoran Hu, Connor M Kennedy, Panayotis G. Kevrekidis, Hongkun Zhang

Abstract: A variety of approaches using compartmental models have been used to study the COVID-19 pandemic and the usage of machine learning methods with these models has had particularly notable success. We present here an approach toward analyzing accessible data on Covid-19's U.S. development using a variation of the "Physics Informed Neural Networks" (PINN) which is capable of using the knowledge of the… ▽ More A variety of approaches using compartmental models have been used to study the COVID-19 pandemic and the usage of machine learning methods with these models has had particularly notable success. We present here an approach toward analyzing accessible data on Covid-19's U.S. development using a variation of the "Physics Informed Neural Networks" (PINN) which is capable of using the knowledge of the model to aid learning. We illustrate the challenges of using the standard PINN approach, then how with appropriate and novel modifications to the loss function the network can perform well even in our case of incomplete information. Aspects of identifiability of the model parameters are also assessed, as well as methods of denoising available data using a wavelet transform. Finally, we discuss the capability of the neural network methodology to work with models of varying parameter values, as well as a concrete application in estimating how effectively cases are being tested for in a population, providing a ranking of U.S. states by means of their respective testing. △ Less

Submitted 17 August, 2022; v1 submitted 1 August, 2022; originally announced August 2022.

Comments: 22 pages, 8 figures, to be submitted to Viruses

Bayesian Quickest Change Detection of an Intruder in Acknowledgments for Private Remote State Estimation

Authors: Justin M. Kennedy, Jason J. Ford, Daniel E. Quevedo

Abstract: For geographically separated cyber-physical systems, state estimation at a remote monitoring or control site is important to ensure stability and reliability of the system. Often for safety or commercial reasons it is necessary to ensure confidentiality of the process state and control information. A current topic of interest is the private transmission of confidential state information. Many tran… ▽ More For geographically separated cyber-physical systems, state estimation at a remote monitoring or control site is important to ensure stability and reliability of the system. Often for safety or commercial reasons it is necessary to ensure confidentiality of the process state and control information. A current topic of interest is the private transmission of confidential state information. Many transmission encoding schemes rely on acknowledgments, which may be susceptible to interference from an adversary. We consider a stealthy intruder that selectively blocks acknowledgments allowing an eavesdropper to obtain a reliable state estimate defeating an encoding scheme. We utilize Bayesian Quickest Change Detection techniques to quickly detect online the presence of an intruder at both the remote transmitter and receiver. △ Less

Submitted 15 December, 2022; v1 submitted 17 July, 2022; originally announced July 2022.

Comments: 6 pages, 5 figures

Journal ref: Australian and New Zealand Control Conference, 24-25 November 2022, Gold Coast, Australia

Centralized Model-Predictive Control with Human-Driver Interaction for Platooning

Authors: Justin M. Kennedy, Julian Heinovski, Daniel E. Quevedo, Falko Dressler

Abstract: Cooperative adaptive cruise control presents an opportunity to improve road transportation through increase in road capacity and reduction in energy use and accidents. Clever design of control algorithms and communication systems is required to ensure that the vehicle platoon is stable and meets desired safety requirements. In this paper, we propose a centralized model predictive controller for a… ▽ More Cooperative adaptive cruise control presents an opportunity to improve road transportation through increase in road capacity and reduction in energy use and accidents. Clever design of control algorithms and communication systems is required to ensure that the vehicle platoon is stable and meets desired safety requirements. In this paper, we propose a centralized model predictive controller for a heterogeneous platoon of vehicles to reach a desired platoon velocity and individual inter-vehicle distances with driver-selected headway time. As a novel concept, we allow for interruption from a human driver in the platoon that temporarily takes control of their vehicle with the assumption that the driver will, at minimum, obey legal velocity limits and the physical performance constraints of their vehicle. The finite horizon cost function of our proposed platoon controller is inspired from the infinite horizon design. To the best of our knowledge, this is the first platoon controller that integrates human-driven vehicles. We illustrate the performance of our proposed design with a numerical study, demonstrating that the safety distance, velocity, and actuation constraints are obeyed. Additionally, in simulation we illustrate a key property of string stability where the impact of a disturbance is reduced through the platoon. △ Less

Submitted 18 May, 2023; v1 submitted 18 May, 2022; originally announced May 2022.

Comments: 17 pages, 8 figures, to appear in IEEE Transactions on Vehicular Technology

Journal ref: IEEE Transactions on Vehicular Technology, vol. 72 (10), pp. 12664-12680, October 2023