Showing 1–50 of 62 results for author: Jensfelt, P

Accelerating Large-scale Bundle Adjustment for LiDAR Mapping via Parallel Computing

Authors: Yixi Cai, Rundong Li, Yuhan Xie, Qingwen Zhang, Patric Jensfelt, Fu Zhang

Abstract: LiDAR bundle adjustment is widely utilized in mapping to construct globally consistent point cloud maps. In this paper, we propose the first fully parallel computing framework to accelerate LiDAR bundle adjustment for large-scale mapping, incorporating three key techniques. First, we design an adaptive, asynchronous data loading strategy to efficiently process large-scale point cloud datasets on m… ▽ More LiDAR bundle adjustment is widely utilized in mapping to construct globally consistent point cloud maps. In this paper, we propose the first fully parallel computing framework to accelerate LiDAR bundle adjustment for large-scale mapping, incorporating three key techniques. First, we design an adaptive, asynchronous data loading strategy to efficiently process large-scale point cloud datasets on memory-constrained GPUs. Secondly, we present a novel bottom-up voxelization method for extracting planar features, enabling fully parallelized pre-processing. Thirdly, we build upon a majorization-minimization formulation to accelerate compute-intensive tasks in the optimization via parallel computation, including the computation of residuals, Jacobian and Hessian matrices, and a parallel increment solver. To support our design, we provide both theoretical and experimental analysis of the time complexity of our approach. Extensive benchmarking on large-scale public datasets across various computational platforms validates the robustness and adaptability of our approach, achieving up to a tenfold improvement in computational efficiency while preserving mapping accuracy comparable to state-of-the-art methods. To benefit future research, the implementation code is available on GitHub. △ Less

Submitted 14 August, 2026; originally announced August 2026.

Comments: Accepted by IEEE International Conference on Automation Science and Engineering (CASE), 2026

GESTO: Human-Centric Spatio-Temporal Memory for Reasoning in Dynamic Scenes

Authors: Ermanno Bartoli, Buwei He, Dennis Rotondi, Sebastian Koch, Federico Tombari, Kai O. Arras, Patric Jensfelt, Yixi Cai, Iolanda Leite

Abstract: Robots operating in human environments need memories that capture not only what objects exist and where, but also how people use them over time and how individual interactions compose into goal-directed activities. Existing 4D scene graphs preserve object and place histories but omit activity structure, whereas activity representations are either not grounded in persistent 3D scenes or rely on ext… ▽ More Robots operating in human environments need memories that capture not only what objects exist and where, but also how people use them over time and how individual interactions compose into goal-directed activities. Existing 4D scene graphs preserve object and place histories but omit activity structure, whereas activity representations are either not grounded in persistent 3D scenes or rely on externally provided event boundaries and object associations. We present GESTO (Grounded Event and Spatio-Temporal memOry), a spatio-temporal memory that couples a persistent 4D scene graph with a two-level hierarchy of atomic human--object interactions and goal-driven events. From an RGB-D observation stream, GESTO automatically extracts timestamped interactions, grounds them to persistent scene entities, groups them into events, and uses event context to refine uncertain object associations. A relation-aware tool-calling agent queries the resulting memory for activity-centric spatio-temporal reasoning. We evaluate GESTO on the reproducible text, binary, and time categories of an existing benchmark, together with 40 new Space2Event and Event2Space queries. GESTO achieves scores of 0.71, 0.75, and 0.70 on the standard categories, approaching a method supplied with ground-truth event and object grounding, while substantially outperforming the same reasoning framework when these inputs are removed. It further achieves 0.73 and 0.75 on Space2Event and Event2Space queries. Ablations show that hierarchical event structure and context-aware grounding refinement provide complementary benefits, supporting activity-grounded hierarchical memory for retrospective reasoning in dynamic human environments. △ Less

Submitted 11 August, 2026; originally announced August 2026.

Risk-Aware Belief Control Barrier Functions over Random Finite Sets

Authors: Shaohang Han, Gang Chen, Yixi Cai, Ignacio Torroba, Ivan Stenius, Patric Jensfelt, Javier Alonso-Mora, Jana Tumova

Abstract: Ensuring robot safety in unknown, dynamic environments is a fundamental requirement. It involves inferring the states of an unknown and time-varying number of moving objects from noisy, incomplete measurements. We address safe control under the induced multi-object state uncertainty with a risk-aware belief control barrier function (BCBF) framework. The uncertainty is captured by a random finite s… ▽ More Ensuring robot safety in unknown, dynamic environments is a fundamental requirement. It involves inferring the states of an unknown and time-varying number of moving objects from noisy, incomplete measurements. We address safe control under the induced multi-object state uncertainty with a risk-aware belief control barrier function (BCBF) framework. The uncertainty is captured by a random finite set (RFS) belief, estimated by a sequential Monte Carlo probability hypothesis density (SMC-PHD) filter that represents it with a set of particles. Building directly on these particles, we construct a nonsmooth BCBF, establish forward invariance of the safe set under continuous prediction, and derive an explicit condition under which discrete updates preserve safety. Simulation and real-world underwater experiments demonstrate the effectiveness and efficiency of the proposed approach. △ Less

Submitted 16 July, 2026; originally announced July 2026.

HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-training

Authors: Maciej Wozniak, Jesper Ericsson, Hariprasath Govindarajan, Truls Nyberg, Thomas Gustafsson, Patric Jensfelt, Olov Andersson

Abstract: Leveraging Vision Foundation Models (VFMs) for camera-to-LiDAR knowledge distillation offers a promising solution to the scarcity of annotated data needed to represent the immense geometric and kinematic diversity of real-world autonomous driving (AD). However, current approaches typically treat VFMs as black-box teachers, relying exclusively on frame-wise feature similarity. Consequently, they do… ▽ More Leveraging Vision Foundation Models (VFMs) for camera-to-LiDAR knowledge distillation offers a promising solution to the scarcity of annotated data needed to represent the immense geometric and kinematic diversity of real-world autonomous driving (AD). However, current approaches typically treat VFMs as black-box teachers, relying exclusively on frame-wise feature similarity. Consequently, they do not fully exploit the teacher's layer-wise semantic structure and global context, as well as the rich spatiotemporal information inherent in LiDAR sequences. We propose HilDA, a self-supervised pretraining framework for LiDAR backbones that better captures the semantic what and geometric where needed for driving tasks. HilDA combines hierarchical distillation comprising multi-layer distillation for progressive semantic alignment and global context distillation for scene-level semantics, with a temporal occupancy diffusion objective promoting spatiotemporal consistency. Models pre-trained with HilDA achieve state-of-the-art results on cross-modal distillation benchmarks and outperform models trained via prior distillation approaches on 3D object detection, scene flow, and semantic occupancy prediction. Code available at: https://maxiuw.github.io/hilda. △ Less

Submitted 23 June, 2026; v1 submitted 18 June, 2026; originally announced June 2026.

Comments: Accepted to ECCV 2026. Maciej and Jesper contributed equally

Radar-Informed 3D Multi-Object Tracking under Adverse Conditions

Authors: Bingxue Xu, Emil Hedemalm, Ajinkya Khoche, Patric Jensfelt

Abstract: The challenge of 3D multi-object tracking is achieving robustness in real-world applications, for example under adverse conditions and maintaining consistency as distance increases. To overcome these challenges, sensor fusion approaches that combine LiDAR, cameras, and radar have emerged. However, existing multimodal methods usually treat radar as another learned feature inside the network. When t… ▽ More The challenge of 3D multi-object tracking is achieving robustness in real-world applications, for example under adverse conditions and maintaining consistency as distance increases. To overcome these challenges, sensor fusion approaches that combine LiDAR, cameras, and radar have emerged. However, existing multimodal methods usually treat radar as another learned feature inside the network. When the overall model degrades in difficult environments, the robustness advantages that radar could provide are also reduced. In this paper we propose RadarMOT, a radar-informed 3D multi-object tracking framework that explicitly uses radar point clouds as additional observations to refine state estimation and recover objects missed by the detector at long ranges. Evaluations on the MAN-TruckScenes dataset show that RadarMOT consistently improves the Average Multi-Object Tracking Accuracy (AMOTA) by 12.7\% at long range and up to 10.3\% in adverse weather. The code will be available at https://github.com/bingxue-xu/radarmot △ Less

Submitted 21 April, 2026; v1 submitted 15 April, 2026; originally announced April 2026.

Comments: 7 pages, 5 figures

SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data

Authors: Qingwen Zhang, Xiaomeng Zhu, Chenhan Jiang, Patric Jensfelt

Abstract: Reliable 3D dynamic perception requires models that can anticipate motion beyond predefined categories, yet progress is hindered by the scarcity of dense, high-quality motion annotations. While self-supervision on unlabeled real data offers a path forward, empirical evidence suggests that scaling unlabeled data fails to close the performance gap due to noisy proxy signals. In this paper, we propos… ▽ More Reliable 3D dynamic perception requires models that can anticipate motion beyond predefined categories, yet progress is hindered by the scarcity of dense, high-quality motion annotations. While self-supervision on unlabeled real data offers a path forward, empirical evidence suggests that scaling unlabeled data fails to close the performance gap due to noisy proxy signals. In this paper, we propose learning robust real-world motion priors entirely from scalable simulation. We introduce SynFlow, a data generation pipeline for large-scale synthetic LiDAR scene flow. Unlike prior works that prioritize sensor-specific realism, SynFlow employs a motion-oriented strategy to synthesize diverse kinematic patterns across 4,000 sequences ($\sim$940k frames), termed SynFlow-4k. This represents a $34\times$ scale-up in annotated volume over existing real-world benchmarks. Our experiments demonstrate that SynFlow-4k provides a highly domain-invariant motion prior. In a zero-shot regime, models trained only on our synthetic data generalize across multiple real-world benchmarks, comparable to in-domain supervised baselines on nuScenes and outperforming state-of-the-art methods on TruckScenes by 31.8%. Furthermore, SynFlow-4k serves as a label-efficient foundation: fine-tuning with only 5% of real-world labels surpasses models trained from scratch on the full available budget. We open-source the pipeline and dataset to facilitate research in generalizable 3D motion estimation. More detail can be found at https://kin-zhang.github.io/SynFlow. △ Less

Submitted 28 July, 2026; v1 submitted 10 April, 2026; originally announced April 2026.

Comments: ECCV 2026; 18 pages, 4 figures

TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation

Authors: Qingwen Zhang, Chenhan Jiang, Xiaomeng Zhu, Yunqi Miao, Yushan Zhang, Olov Andersson, Patric Jensfelt

Abstract: Self-supervised feed-forward methods for scene flow estimation offer real-time efficiency, but their supervision from two-frame point correspondences is unreliable and often breaks down under occlusions. Multi-frame supervision has the potential to provide more stable guidance by incorporating motion cues from past frames, yet naive extensions of two-frame objectives are ineffective because point… ▽ More Self-supervised feed-forward methods for scene flow estimation offer real-time efficiency, but their supervision from two-frame point correspondences is unreliable and often breaks down under occlusions. Multi-frame supervision has the potential to provide more stable guidance by incorporating motion cues from past frames, yet naive extensions of two-frame objectives are ineffective because point correspondences vary abruptly across frames, producing inconsistent signals. In the paper, we present TeFlow, enabling multi-frame supervision for feed-forward models by mining temporally consistent supervision. TeFlow introduces a temporal ensembling strategy that forms reliable supervisory signals by aggregating the most temporally consistent motion cues from a candidate pool built across multiple frames. Extensive evaluations demonstrate that TeFlow establishes a new state-of-the-art for self-supervised feed-forward methods, achieving performance gains of up to 33\% on the challenging Argoverse 2 and nuScenes datasets. Our method performs on par with leading optimization-based methods, yet speeds up 150 times. The code is open-sourced at https://github.com/Kin-Zhang/TeFlow along with trained model weights. △ Less

Submitted 1 April, 2026; v1 submitted 22 February, 2026; originally announced February 2026.

Comments: CVPR 2026; 16 pages, 8 figures

Visible Structure Retrieval for Lightweight Image-Based Relocalisation

Authors: Fereidoon Zangeneh, Leonard Bruns, Amit Dekel, Alessandro Pieropan, Patric Jensfelt

Abstract: Accurate camera pose estimation from an image observation in a previously mapped environment is commonly done through structure-based methods: by finding correspondences between 2D keypoints on the image and 3D structure points in the map. In order to make this correspondence search tractable in large scenes, existing pipelines either rely on search heuristics, or perform image retrieval to reduce… ▽ More Accurate camera pose estimation from an image observation in a previously mapped environment is commonly done through structure-based methods: by finding correspondences between 2D keypoints on the image and 3D structure points in the map. In order to make this correspondence search tractable in large scenes, existing pipelines either rely on search heuristics, or perform image retrieval to reduce the search space by comparing the current image to a database of past observations. However, these approaches result in elaborate pipelines or storage requirements that grow with the number of past observations. In this work, we propose a new paradigm for making structure-based relocalisation tractable. Instead of relying on image retrieval or search heuristics, we learn a direct mapping from image observations to the visible scene structure in a compact neural network. Given a query image, a forward pass through our novel visible structure retrieval network allows obtaining the subset of 3D structure points in the map that the image views, thus reducing the search space of 2D-3D correspondences. We show that our proposed method enables performing localisation with an accuracy comparable to the state of the art, while requiring lower computational and storage footprint. △ Less

Submitted 16 November, 2025; originally announced November 2025.

Comments: Accepted at BMVC 2025

BlendCLIP: Bridging Synthetic and Real Domains for Zero-Shot 3D Object Classification with Multimodal Pretraining

Authors: Ajinkya Khoche, Gergő László Nagy, Maciej Wozniak, Thomas Gustafsson, Patric Jensfelt

Abstract: Zero-shot 3D object classification is crucial for real-world applications like autonomous driving, however it is often hindered by a significant domain gap between the synthetic data used for training and the sparse, noisy LiDAR scans encountered in the real-world. Current methods trained solely on synthetic data fail to generalize to outdoor scenes, while those trained only on real data lack the… ▽ More Zero-shot 3D object classification is crucial for real-world applications like autonomous driving, however it is often hindered by a significant domain gap between the synthetic data used for training and the sparse, noisy LiDAR scans encountered in the real-world. Current methods trained solely on synthetic data fail to generalize to outdoor scenes, while those trained only on real data lack the semantic diversity to recognize rare or unseen objects. We introduce BlendCLIP, a multimodal pretraining framework that bridges this synthetic-to-real gap by strategically combining the strengths of both domains. We first propose a pipeline to generate a large-scale dataset of object-level triplets -- consisting of a point cloud, image, and text description -- mined directly from real-world driving data and human annotated 3D boxes. Our core contribution is a curriculum-based data mixing strategy that first grounds the model in the semantically rich synthetic CAD data before progressively adapting it to the specific characteristics of real-world scans. Our experiments show that our approach is highly label-efficient: introducing as few as 1.5\% real-world samples per batch into training boosts zero-shot accuracy on the nuScenes benchmark by 27\%. Consequently, our final model achieves state-of-the-art performance on challenging outdoor datasets like nuScenes and TruckScenes, improving over the best prior method by 19.3\% on nuScenes, while maintaining strong generalization on diverse synthetic benchmarks. Our findings demonstrate that effective domain adaptation, not full-scale real-world annotation, is the key to unlocking robust open-vocabulary 3D perception. Our code and dataset will be released upon acceptance on https://github.com/kesu1/BlendCLIP. △ Less

Submitted 20 October, 2025; originally announced October 2025.

Comments: Under Review

Social 3D Scene Graphs: Modeling Human Actions and Relations for Interactive Service Robots

Authors: Ermanno Bartoli, Dennis Rotondi, Buwei He, Patric Jensfelt, Kai O. Arras, Iolanda Leite

Abstract: Understanding how people interact with their surroundings and each other is essential for enabling robots to act in socially compliant and context-aware ways. While 3D Scene Graphs have emerged as a powerful semantic representation for scene understanding, existing approaches largely ignore humans in the scene, also due to the lack of annotated human-environment relationships. Moreover, existing m… ▽ More Understanding how people interact with their surroundings and each other is essential for enabling robots to act in socially compliant and context-aware ways. While 3D Scene Graphs have emerged as a powerful semantic representation for scene understanding, existing approaches largely ignore humans in the scene, also due to the lack of annotated human-environment relationships. Moreover, existing methods typically capture only open-vocabulary relations from single image frames, which limits their ability to model long-range interactions beyond the observed content. We introduce Social 3D Scene Graphs, an augmented 3D Scene Graph representation that captures humans, their attributes, activities and relationships in the environment, both local and remote, using an open-vocabulary framework. Furthermore, we introduce a new benchmark consisting of synthetic environments with comprehensive human-scene relationship annotations and diverse types of queries for evaluating social scene understanding in 3D. The experiments demonstrate that our representation improves human activity prediction and reasoning about human-environment relations, paving the way toward socially intelligent robots. △ Less

Submitted 6 July, 2026; v1 submitted 29 September, 2025; originally announced September 2025.

Comments: Equal contribution from E. Bartoli and D. Rotondi. Paper accepted at IROS 2026

ArgoTweak: Towards Self-Updating HD Maps through Structured Priors

Authors: Lena Wild, Rafael Valencia, Patric Jensfelt

Abstract: Reliable integration of prior information is crucial for self-verifying and self-updating HD maps. However, no public dataset includes the required triplet of prior maps, current maps, and sensor data. As a result, existing methods must rely on synthetic priors, which create inconsistencies and lead to a significant sim2real gap. To address this, we introduce ArgoTweak, the first dataset to comple… ▽ More Reliable integration of prior information is crucial for self-verifying and self-updating HD maps. However, no public dataset includes the required triplet of prior maps, current maps, and sensor data. As a result, existing methods must rely on synthetic priors, which create inconsistencies and lead to a significant sim2real gap. To address this, we introduce ArgoTweak, the first dataset to complete the triplet with realistic map priors. At its core, ArgoTweak employs a bijective mapping framework, breaking down large-scale modifications into fine-grained atomic changes at the map element level, thus ensuring interpretability. This paradigm shift enables accurate change detection and integration while preserving unchanged elements with high fidelity. Experiments show that training models on ArgoTweak significantly reduces the sim2real gap compared to synthetic priors. Extensive ablations further highlight the impact of structured priors and detailed change annotations. By establishing a benchmark for explainable, prior-aided HD mapping, ArgoTweak advances scalable, self-improving mapping solutions. The dataset, baselines, map modification toolbox, and further resources are available at https://kth-rpl.github.io/ArgoTweak/. △ Less

Submitted 10 September, 2025; originally announced September 2025.

Comments: ICCV 2025

DoGFlow: Self-Supervised LiDAR Scene Flow via Cross-Modal Doppler Guidance

Authors: Ajinkya Khoche, Qingwen Zhang, Yixi Cai, Sina Sharif Mansouri, Patric Jensfelt

Abstract: Accurate 3D scene flow estimation is critical for autonomous systems to navigate dynamic environments safely, but creating the necessary large-scale, manually annotated datasets remains a significant bottleneck for developing robust perception models. Current self-supervised methods struggle to match the performance of fully supervised approaches, especially in challenging long-range and adverse w… ▽ More Accurate 3D scene flow estimation is critical for autonomous systems to navigate dynamic environments safely, but creating the necessary large-scale, manually annotated datasets remains a significant bottleneck for developing robust perception models. Current self-supervised methods struggle to match the performance of fully supervised approaches, especially in challenging long-range and adverse weather scenarios, while supervised methods are not scalable due to their reliance on expensive human labeling. We introduce DoGFlow, a novel self-supervised framework that recovers full 3D object motions for LiDAR scene flow estimation without requiring any manual ground truth annotations. This paper presents our cross-modal label transfer approach, where DoGFlow computes motion pseudo-labels in real-time directly from 4D radar Doppler measurements and transfers them to the LiDAR domain using dynamic-aware association and ambiguity-resolved propagation. On the challenging MAN TruckScenes dataset, DoGFlow substantially outperforms existing self-supervised methods and improves label efficiency by enabling LiDAR backbones to achieve over 90% of fully supervised performance with only 10% of the ground truth data. For more details, please visit https://ajinkyakhoche.github.io/DogFlow/ △ Less

Submitted 25 August, 2025; originally announced August 2025.

Comments: Under Review

DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method

Authors: Qingwen Zhang, Xiaomeng Zhu, Yushan Zhang, Yixi Cai, Olov Andersson, Patric Jensfelt

Abstract: Previous dominant methods for scene flow estimation focus mainly on input from two consecutive frames, neglecting valuable information in the temporal domain. While recent trends shift towards multi-frame reasoning, they suffer from rapidly escalating computational costs as the number of frames grows. To leverage temporal information more efficiently, we propose DeltaFlow ($Δ$Flow), a lightweight… ▽ More Previous dominant methods for scene flow estimation focus mainly on input from two consecutive frames, neglecting valuable information in the temporal domain. While recent trends shift towards multi-frame reasoning, they suffer from rapidly escalating computational costs as the number of frames grows. To leverage temporal information more efficiently, we propose DeltaFlow ($Δ$Flow), a lightweight 3D framework that captures motion cues via a $Δ$ scheme, extracting temporal features with minimal computational cost, regardless of the number of frames. Additionally, scene flow estimation faces challenges such as imbalanced object class distributions and motion inconsistency. To tackle these issues, we introduce a Category-Balanced Loss to enhance learning across underrepresented classes and an Instance Consistency Loss to enforce coherent object motion, improving flow accuracy. Extensive evaluations on the Argoverse 2, Waymo and nuScenes datasets show that $Δ$Flow achieves state-of-the-art performance with up to 22% lower error and $2\times$ faster inference compared to the next-best multi-frame supervised method, while also demonstrating a strong cross-domain generalization ability. The code is open-sourced at https://github.com/Kin-Zhang/DeltaFlow along with trained model weights. △ Less

Submitted 22 December, 2025; v1 submitted 23 August, 2025; originally announced August 2025.

Comments: NeurIPS 2025 Spotlight, 18 pages (10 main pages + 8 supp materail), 11 figures, code at https://github.com/Kin-Zhang/DeltaFlow

PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving

Authors: Maciej K. Wozniak, Lianhang Liu, Yixi Cai, Patric Jensfelt

Abstract: While end-to-end autonomous driving models show promising results, their practical deployment is often hindered by large model sizes, a reliance on expensive LiDAR sensors and computationally intensive BEV feature representations. This limits their scalability, especially for mass-market vehicles equipped only with cameras. To address these challenges, we propose PRIX (Plan from Raw Pixels). Our n… ▽ More While end-to-end autonomous driving models show promising results, their practical deployment is often hindered by large model sizes, a reliance on expensive LiDAR sensors and computationally intensive BEV feature representations. This limits their scalability, especially for mass-market vehicles equipped only with cameras. To address these challenges, we propose PRIX (Plan from Raw Pixels). Our novel and efficient end-to-end driving architecture operates using only camera data, without explicit BEV representation and forgoing the need for LiDAR. PRIX leverages a visual feature extractor coupled with a generative planning head to predict safe trajectories from raw pixel inputs directly. A core component of our architecture is the Context-aware Recalibration Transformer (CaRT), a novel module designed to effectively enhance multi-level visual features for more robust planning. We demonstrate through comprehensive experiments that PRIX achieves state-of-the-art performance on the NavSim and nuScenes benchmarks, matching the capabilities of larger, multimodal diffusion planners while being significantly more efficient in terms of inference speed and model size, making it a practical solution for real-world deployment. Our work is open-source and the code will be at https://maxiuw.github.io/prix. △ Less

Submitted 12 April, 2026; v1 submitted 23 July, 2025; originally announced July 2025.

Comments: Accepted for Robotics and Automation Letters (RA-L) and will be presented at iROS 2026

MatChA: Cross-Algorithm Matching with Feature Augmentation

Authors: Paula Carbó Cubero, Alberto Jaenal Gálvez, André Mateus, José Araújo, Patric Jensfelt

Abstract: State-of-the-art methods fail to solve visual localization in scenarios where different devices use different sparse feature extraction algorithms to obtain keypoints and their corresponding descriptors. Translating feature descriptors is enough to enable matching. However, performance is drastically reduced in cross-feature detector cases, because current solutions assume common keypoints. This m… ▽ More State-of-the-art methods fail to solve visual localization in scenarios where different devices use different sparse feature extraction algorithms to obtain keypoints and their corresponding descriptors. Translating feature descriptors is enough to enable matching. However, performance is drastically reduced in cross-feature detector cases, because current solutions assume common keypoints. This means that the same detector has to be used, which is rarely the case in practice when different descriptors are used. The low repeatability of keypoints, in addition to non-discriminatory and non-distinctive descriptors, make the identification of true correspondences extremely challenging. We present the first method tackling this problem, which performs feature descriptor augmentation targeting cross-detector feature matching, and then feature translation to a latent space. We show that our method significantly improves image matching and visual localization in the cross-feature scenario and evaluate the proposed method on several benchmarks. △ Less

Submitted 27 June, 2025; originally announced June 2025.

Quantifying Epistemic Uncertainty in Absolute Pose Regression

Authors: Fereidoon Zangeneh, Amit Dekel, Alessandro Pieropan, Patric Jensfelt

Abstract: Visual relocalization is the task of estimating the camera pose given an image it views. Absolute pose regression offers a solution to this task by training a neural network, directly regressing the camera pose from image features. While an attractive solution in terms of memory and compute efficiency, absolute pose regression's predictions are inaccurate and unreliable outside the training domain… ▽ More Visual relocalization is the task of estimating the camera pose given an image it views. Absolute pose regression offers a solution to this task by training a neural network, directly regressing the camera pose from image features. While an attractive solution in terms of memory and compute efficiency, absolute pose regression's predictions are inaccurate and unreliable outside the training domain. In this work, we propose a novel method for quantifying the epistemic uncertainty of an absolute pose regression model by estimating the likelihood of observations within a variational framework. Beyond providing a measure of confidence in predictions, our approach offers a unified model that also handles observation ambiguities, probabilistically localizing the camera in the presence of repetitive structures. Our method outperforms existing approaches in capturing the relation between uncertainty and prediction error. △ Less

Submitted 9 April, 2025; originally announced April 2025.

Information Gain Is Not All You Need

Authors: Ludvig Ericson, José Pedro, Patric Jensfelt

Abstract: Autonomous exploration in mobile robotics often involves a trade-off between two objectives: maximizing environmental coverage and minimizing the total path length. In the widely used information gain paradigm, exploration is guided by the expected value of observations. While this approach is effective under budget-constrained settings--where only a limited number of observations can be made--it… ▽ More Autonomous exploration in mobile robotics often involves a trade-off between two objectives: maximizing environmental coverage and minimizing the total path length. In the widely used information gain paradigm, exploration is guided by the expected value of observations. While this approach is effective under budget-constrained settings--where only a limited number of observations can be made--it fails to align with quality-constrained scenarios, in which the robot must fully explore the environment to a desired level of certainty or quality. In such cases, total information gain is effectively fixed, and maximizing it per step can lead to inefficient, greedy behavior and unnecessary backtracking. This paper argues that information gain should not serve as an optimization objective in quality-constrained exploration. Instead, it should be used to filter viable candidate actions. We propose a novel heuristic, distance advantage, which selects candidate frontiers based on a trade-off between proximity to the robot and remoteness from other frontiers. This heuristic aims to reduce future detours by prioritizing exploration of isolated regions before the robot's opportunity to visit them efficiently has passed. We evaluate our method in simulated environments against classical frontier-based exploration and gain-maximizing approaches. Results show that distance advantage significantly reduces total path length across a variety of environments, both with and without access to prior map predictions. Our findings challenge the assumption that more accurate gain estimation improves performance and offer a more suitable alternative for the quality-constrained exploration paradigm. △ Less

Submitted 20 April, 2025; v1 submitted 28 March, 2025; originally announced April 2025.

Comments: 9 pages, 6 figures, under review

HiMo: High-Speed Objects Motion Compensation in Point Clouds

Authors: Qingwen Zhang, Ajinkya Khoche, Yi Yang, Li Ling, Sina Sharif Mansouri, Olov Andersson, Patric Jensfelt

Abstract: LiDAR point cloud is essential for autonomous vehicles, but motion distortions from dynamic objects degrade the data quality. While previous work has considered distortions caused by ego motion, distortions caused by other moving objects remain largely overlooked, leading to errors in object shape and position. This distortion is particularly pronounced in high-speed environments such as highways… ▽ More LiDAR point cloud is essential for autonomous vehicles, but motion distortions from dynamic objects degrade the data quality. While previous work has considered distortions caused by ego motion, distortions caused by other moving objects remain largely overlooked, leading to errors in object shape and position. This distortion is particularly pronounced in high-speed environments such as highways and in multi-LiDAR configurations, a common setup for heavy vehicles. To address this challenge, we introduce HiMo, a pipeline that repurposes scene flow estimation for non-ego motion compensation, correcting the representation of dynamic objects in point clouds. During the development of HiMo, we observed that existing self-supervised scene flow estimators often produce degenerate or inconsistent estimates under high-speed distortion. We further propose SeFlow++, a real-time scene flow estimator that achieves state-of-the-art performance on both scene flow and motion compensation. Since well-established motion distortion metrics are absent in the literature, we introduce two evaluation metrics: compensation accuracy at a point level and shape similarity of objects. We validate HiMo through extensive experiments on Argoverse 2, ZOD, and a newly collected real-world dataset featuring highway driving and multi-LiDAR-equipped heavy vehicles. Our findings show that HiMo improves the geometric consistency and visual fidelity of dynamic objects in LiDAR point clouds, benefiting downstream tasks such as semantic segmentation and 3D detection. See https://kin-zhang.github.io/HiMo for more details. △ Less

Submitted 30 November, 2025; v1 submitted 2 March, 2025; originally announced March 2025.

Comments: 15 pages, 13 figures, Published in Transactions on Robotics (Volume 41)

SSF: Sparse Long-Range Scene Flow for Autonomous Driving

Authors: Ajinkya Khoche, Qingwen Zhang, Laura Pereira Sanchez, Aron Asefaw, Sina Sharif Mansouri, Patric Jensfelt

Abstract: Scene flow enables an understanding of the motion characteristics of the environment in the 3D world. It gains particular significance in the long-range, where object-based perception methods might fail due to sparse observations far away. Although significant advancements have been made in scene flow pipelines to handle large-scale point clouds, a gap remains in scalability with respect to long-r… ▽ More Scene flow enables an understanding of the motion characteristics of the environment in the 3D world. It gains particular significance in the long-range, where object-based perception methods might fail due to sparse observations far away. Although significant advancements have been made in scene flow pipelines to handle large-scale point clouds, a gap remains in scalability with respect to long-range. We attribute this limitation to the common design choice of using dense feature grids, which scale quadratically with range. In this paper, we propose Sparse Scene Flow (SSF), a general pipeline for long-range scene flow, adopting a sparse convolution based backbone for feature extraction. This approach introduces a new challenge: a mismatch in size and ordering of sparse feature maps between time-sequential point scans. To address this, we propose a sparse feature fusion scheme, that augments the feature maps with virtual voxels at missing locations. Additionally, we propose a range-wise metric that implicitly gives greater importance to faraway points. Our method, SSF, achieves state-of-the-art results on the Argoverse2 dataset, demonstrating strong performance in long-range scene flow estimation. Our code will be released at https://github.com/KTH-RPL/SSF.git. △ Less

Submitted 29 January, 2025; originally announced January 2025.

Comments: 7 pages, 3 figures, accepted to International Conference on Robotics and Automation (ICRA) 2025

Conditional Variational Autoencoders for Probabilistic Pose Regression

Authors: Fereidoon Zangeneh, Leonard Bruns, Amit Dekel, Alessandro Pieropan, Patric Jensfelt

Abstract: Robots rely on visual relocalization to estimate their pose from camera images when they lose track. One of the challenges in visual relocalization is repetitive structures in the operation environment of the robot. This calls for probabilistic methods that support multiple hypotheses for robot's pose. We propose such a probabilistic method to predict the posterior distribution of camera poses giv… ▽ More Robots rely on visual relocalization to estimate their pose from camera images when they lose track. One of the challenges in visual relocalization is repetitive structures in the operation environment of the robot. This calls for probabilistic methods that support multiple hypotheses for robot's pose. We propose such a probabilistic method to predict the posterior distribution of camera poses given an observed image. Our proposed training strategy results in a generative model of camera poses given an image, which can be used to draw samples from the pose posterior distribution. Our method is streamlined and well-founded in theory and outperforms existing methods on localization in presence of ambiguities. △ Less

Submitted 7 October, 2024; originally announced October 2024.

Comments: Accepted at IROS 2024

Fusion in Context: A Multimodal Approach to Affective State Recognition

Authors: Youssef Mohamed, Severin Lemaignan, Arzu Guneysu, Patric Jensfelt, Christian Smith

Abstract: Accurate recognition of human emotions is a crucial challenge in affective computing and human-robot interaction (HRI). Emotional states play a vital role in shaping behaviors, decisions, and social interactions. However, emotional expressions can be influenced by contextual factors, leading to misinterpretations if context is not considered. Multimodal fusion, combining modalities like facial exp… ▽ More Accurate recognition of human emotions is a crucial challenge in affective computing and human-robot interaction (HRI). Emotional states play a vital role in shaping behaviors, decisions, and social interactions. However, emotional expressions can be influenced by contextual factors, leading to misinterpretations if context is not considered. Multimodal fusion, combining modalities like facial expressions, speech, and physiological signals, has shown promise in improving affect recognition. This paper proposes a transformer-based multimodal fusion approach that leverages facial thermal data, facial action units, and textual context information for context-aware emotion recognition. We explore modality-specific encoders to learn tailored representations, which are then fused using additive fusion and processed by a shared transformer encoder to capture temporal dependencies and interactions. The proposed method is evaluated on a dataset collected from participants engaged in a tangible tabletop Pacman game designed to induce various affective states. Our results demonstrate the effectiveness of incorporating contextual information and multimodal fusion for affective state recognition. △ Less

Submitted 18 September, 2024; originally announced September 2024.

ExelMap: Explainable Element-based HD-Map Change Detection and Update

Authors: Lena Wild, Ludvig Ericson, Rafael Valencia, Patric Jensfelt

Abstract: Acquisition and maintenance are central problems in deploying high-definition (HD) maps for autonomous driving, with two lines of research prevalent in current literature: Online HD map generation and HD map change detection. However, the generated map's quality is currently insufficient for safe deployment, and many change detection approaches fail to precisely localize and extract the changed ma… ▽ More Acquisition and maintenance are central problems in deploying high-definition (HD) maps for autonomous driving, with two lines of research prevalent in current literature: Online HD map generation and HD map change detection. However, the generated map's quality is currently insufficient for safe deployment, and many change detection approaches fail to precisely localize and extract the changed map elements, hence lacking explainability and hindering a potential fleet-based cooperative HD map update. In this paper, we propose the novel task of explainable element-based HD map change detection and update. In extending recent approaches that use online mapping techniques informed with an outdated map prior for HD map updating, we present ExelMap, an explainable element-based map updating strategy that specifically identifies changed map elements. In this context, we discuss how currently used metrics fail to capture change detection performance, while allowing for unfair comparison between prior-less and prior-informed map generation methods. Finally, we present an experimental study on real-world changes related to pedestrian crossings of the Argoverse 2 Map Change Dataset. To the best of our knowledge, this is the first comprehensive problem investigation of real-world end-to-end element-based HD map change detection and update, and ExelMap the first proposed solution. △ Less

Submitted 16 September, 2024; originally announced September 2024.

Comments: 17 pages, 3 figures

HD-maps as Prior Information for Globally Consistent Mapping in GPS-denied Environments

Authors: Waqas Ali, Patric Jensfelt, Thien-Minh Nguyen

Abstract: In recent years, prior maps have become a mainstream tool in autonomous navigation. However, commonly available prior maps are still tailored to control-and-decision tasks, and the use of these maps for localization remains largely unexplored. To bridge this gap, we propose a lidar-based localization and mapping (LOAM) system that can exploit the common HD-maps in autonomous driving scenarios. Spe… ▽ More In recent years, prior maps have become a mainstream tool in autonomous navigation. However, commonly available prior maps are still tailored to control-and-decision tasks, and the use of these maps for localization remains largely unexplored. To bridge this gap, we propose a lidar-based localization and mapping (LOAM) system that can exploit the common HD-maps in autonomous driving scenarios. Specifically, we propose a technique to extract information from the drivable area and ground surface height components of the HD-maps to construct 4DOF pose priors. These pose priors are then further integrated into the pose-graph optimization problem to create a globally consistent 3D map. Experiments show that our scheme can significantly improve the global consistency of the map compared to state-of-the-art lidar-only approaches, proven to be a useful technology to enhance the system's robustness, especially in GPS-denied environment. Moreover, our work also serves as a first step towards long-term navigation of robots in familiar environment, by updating a map. In autonomous driving this could enable updating the HD-maps without sourcing a new from a third party company, which is expensive and introduces delays from change in the world to updated map. △ Less

Submitted 28 July, 2024; originally announced July 2024.

SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving

Authors: Qingwen Zhang, Yi Yang, Peizheng Li, Olov Andersson, Patric Jensfelt

Abstract: Scene flow estimation predicts the 3D motion at each point in successive LiDAR scans. This detailed, point-level, information can help autonomous vehicles to accurately predict and understand dynamic changes in their surroundings. Current state-of-the-art methods require annotated data to train scene flow networks and the expense of labeling inherently limits their scalability. Self-supervised app… ▽ More Scene flow estimation predicts the 3D motion at each point in successive LiDAR scans. This detailed, point-level, information can help autonomous vehicles to accurately predict and understand dynamic changes in their surroundings. Current state-of-the-art methods require annotated data to train scene flow networks and the expense of labeling inherently limits their scalability. Self-supervised approaches can overcome the above limitations, yet face two principal challenges that hinder optimal performance: point distribution imbalance and disregard for object-level motion constraints. In this paper, we propose SeFlow, a self-supervised method that integrates efficient dynamic classification into a learning-based scene flow pipeline. We demonstrate that classifying static and dynamic points helps design targeted objective functions for different motion patterns. We also emphasize the importance of internal cluster consistency and correct object point association to refine the scene flow estimation, in particular on object details. Our real-time capable method achieves state-of-the-art performance on the self-supervised scene flow task on Argoverse 2 and Waymo datasets. The code is open-sourced at https://github.com/KTH-RPL/SeFlow along with trained model weights. △ Less

Submitted 17 September, 2024; v1 submitted 1 July, 2024; originally announced July 2024.

Comments: 25 pages (14 main pages + 11 supp materail), 5 figures, ECCV 2024

Beyond the Frontier: Predicting Unseen Walls from Occupancy Grids by Learning from Floor Plans

Authors: Ludvig Ericson, Patric Jensfelt

Abstract: In this paper, we tackle the challenge of predicting the unseen walls of a partially observed environment as a set of 2D line segments, conditioned on occupancy grids integrated along the trajectory of a 360° LIDAR sensor. A dataset of such occupancy grids and their corresponding target wall segments is collected by navigating a virtual robot between a set of randomly sampled waypoints in a collec… ▽ More In this paper, we tackle the challenge of predicting the unseen walls of a partially observed environment as a set of 2D line segments, conditioned on occupancy grids integrated along the trajectory of a 360° LIDAR sensor. A dataset of such occupancy grids and their corresponding target wall segments is collected by navigating a virtual robot between a set of randomly sampled waypoints in a collection of office-scale floor plans from a university campus. The line segment prediction task is formulated as an autoregressive sequence prediction task, and an attention-based deep network is trained on the dataset. The sequence-based autoregressive formulation is evaluated through predicted information gain, as in frontier-based autonomous exploration, demonstrating significant improvements over both non-predictive estimation and convolution-based image prediction found in the literature. Ablations on key components are evaluated, as well as sensor range and the occupancy grid's metric area. Finally, model generality is validated by predicting walls in a novel floor plan reconstructed on-the-fly in a real-world office environment. △ Less

Submitted 13 June, 2024; originally announced June 2024.

Comments: RA-L, 8 pages

Journal ref: IEEE Robotics and Automation Letters (2024) pp. 2377-3766

BeautyMap: Binary-Encoded Adaptable Ground Matrix for Dynamic Points Removal in Global Maps

Authors: Mingkai Jia, Qingwen Zhang, Bowen Yang, Jin Wu, Ming Liu, Patric Jensfelt

Abstract: Global point clouds that correctly represent the static environment features can facilitate accurate localization and robust path planning. However, dynamic objects introduce undesired ghost tracks that are mixed up with the static environment. Existing dynamic removal methods normally fail to balance the performance in computational efficiency and accuracy. In response, we present BeautyMap to ef… ▽ More Global point clouds that correctly represent the static environment features can facilitate accurate localization and robust path planning. However, dynamic objects introduce undesired ghost tracks that are mixed up with the static environment. Existing dynamic removal methods normally fail to balance the performance in computational efficiency and accuracy. In response, we present BeautyMap to efficiently remove the dynamic points while retaining static features for high-fidelity global maps. Our approach utilizes a binary-encoded matrix to efficiently extract the environment features. With a bit-wise comparison between matrices of each frame and the corresponding map region, we can extract potential dynamic regions. Then we use coarse to fine hierarchical segmentation of the $z$-axis to handle terrain variations. The final static restoration module accounts for the range-visibility of each single scan and protects static points out of sight. Comparative experiments underscore BeautyMap's superior performance in both accuracy and efficiency against other dynamic points removal methods. The code is open-sourced at https://github.com/MKJia/BeautyMap. △ Less

Submitted 12 May, 2024; originally announced May 2024.

Comments: The first two authors are co-first authors. 8 pages, accepted by RA-L

Neural Graph Map: Dense Mapping with Efficient Loop Closure Integration

Authors: Leonard Bruns, Jun Zhang, Patric Jensfelt

Abstract: Neural field-based SLAM methods typically employ a single, monolithic field as their scene representation. This prevents efficient incorporation of loop closure constraints and limits scalability. To address these shortcomings, we propose a novel RGB-D neural mapping framework in which the scene is represented by a collection of lightweight neural fields which are dynamically anchored to the pose… ▽ More Neural field-based SLAM methods typically employ a single, monolithic field as their scene representation. This prevents efficient incorporation of loop closure constraints and limits scalability. To address these shortcomings, we propose a novel RGB-D neural mapping framework in which the scene is represented by a collection of lightweight neural fields which are dynamically anchored to the pose graph of a sparse visual SLAM system. Our approach shows the ability to integrate large-scale loop closures, while requiring only minimal reintegration. Furthermore, we verify the scalability of our approach by demonstrating successful building-scale mapping taking multiple loop closures into account during the optimization, and show that our method outperforms existing state-of-the-art approaches on large scenes in terms of quality and runtime. Our code is available open-source at https://github.com/KTH-RPL/neural_graph_mapping. △ Less

Submitted 25 June, 2025; v1 submitted 6 May, 2024; originally announced May 2024.

Comments: WACV 2025, Project page: https://kth-rpl.github.io/neural_graph_mapping/

Addressing Data Annotation Challenges in Multiple Sensors: A Solution for Scania Collected Datasets

Authors: Ajinkya Khoche, Aron Asefaw, Alejandro Gonzalez, Bogdan Timus, Sina Sharif Mansouri, Patric Jensfelt

Abstract: Data annotation in autonomous vehicles is a critical step in the development of Deep Neural Network (DNN) based models or the performance evaluation of the perception system. This often takes the form of adding 3D bounding boxes on time-sequential and registered series of point-sets captured from active sensors like Light Detection and Ranging (LiDAR) and Radio Detection and Ranging (RADAR). When… ▽ More Data annotation in autonomous vehicles is a critical step in the development of Deep Neural Network (DNN) based models or the performance evaluation of the perception system. This often takes the form of adding 3D bounding boxes on time-sequential and registered series of point-sets captured from active sensors like Light Detection and Ranging (LiDAR) and Radio Detection and Ranging (RADAR). When annotating multiple active sensors, there is a need to motion compensate and translate the points to a consistent coordinate frame and timestamp respectively. However, highly dynamic objects pose a unique challenge, as they can appear at different timestamps in each sensor's data. Without knowing the speed of the objects, their position appears to be different in different sensor outputs. Thus, even after motion compensation, highly dynamic objects are not matched from multiple sensors in the same frame, and human annotators struggle to add unique bounding boxes that capture all objects. This article focuses on addressing this challenge, primarily within the context of Scania collected datasets. The proposed solution takes a track of an annotated object as input and uses the Moving Horizon Estimation (MHE) to robustly estimate its speed. The estimated speed profile is utilized to correct the position of the annotated box and add boxes to object clusters missed by the original annotation. △ Less

Submitted 27 March, 2024; originally announced March 2024.

Comments: Accepted to European Control Conference 2024

UADA3D: Unsupervised Adversarial Domain Adaptation for 3D Object Detection with Sparse LiDAR and Large Domain Gaps

Authors: Maciej K Wozniak, Mattias Hansson, Marko Thiel, Patric Jensfelt

Abstract: In this study, we address a gap in existing unsupervised domain adaptation approaches on LiDAR-based 3D object detection, which have predominantly concentrated on adapting between established, high-density autonomous driving datasets. We focus on sparser point clouds, capturing scenarios from different perspectives: not just from vehicles on the road but also from mobile robots on sidewalks, which… ▽ More In this study, we address a gap in existing unsupervised domain adaptation approaches on LiDAR-based 3D object detection, which have predominantly concentrated on adapting between established, high-density autonomous driving datasets. We focus on sparser point clouds, capturing scenarios from different perspectives: not just from vehicles on the road but also from mobile robots on sidewalks, which encounter significantly different environmental conditions and sensor configurations. We introduce Unsupervised Adversarial Domain Adaptation for 3D Object Detection (UADA3D). UADA3D does not depend on pre-trained source models or teacher-student architectures. Instead, it uses an adversarial approach to directly learn domain-invariant features. We demonstrate its efficacy in various adaptation scenarios, showing significant improvements in both self-driving car and mobile robot domains. Our code is open-source and will be available soon. △ Less

Submitted 21 October, 2024; v1 submitted 26 March, 2024; originally announced March 2024.

Comments: Accepted for IEEE RA-L 2024

MCD: Diverse Large-Scale Multi-Campus Dataset for Robot Perception

Authors: Thien-Minh Nguyen, Shenghai Yuan, Thien Hoang Nguyen, Pengyu Yin, Haozhi Cao, Lihua Xie, Maciej Wozniak, Patric Jensfelt, Marko Thiel, Justin Ziegenbein, Noel Blunder

Abstract: Perception plays a crucial role in various robot applications. However, existing well-annotated datasets are biased towards autonomous driving scenarios, while unlabelled SLAM datasets are quickly over-fitted, and often lack environment and domain variations. To expand the frontier of these fields, we introduce a comprehensive dataset named MCD (Multi-Campus Dataset), featuring a wide range of sen… ▽ More Perception plays a crucial role in various robot applications. However, existing well-annotated datasets are biased towards autonomous driving scenarios, while unlabelled SLAM datasets are quickly over-fitted, and often lack environment and domain variations. To expand the frontier of these fields, we introduce a comprehensive dataset named MCD (Multi-Campus Dataset), featuring a wide range of sensing modalities, high-accuracy ground truth, and diverse challenging environments across three Eurasian university campuses. MCD comprises both CCS (Classical Cylindrical Spinning) and NRE (Non-Repetitive Epicyclic) lidars, high-quality IMUs (Inertial Measurement Units), cameras, and UWB (Ultra-WideBand) sensors. Furthermore, in a pioneering effort, we introduce semantic annotations of 29 classes over 59k sparse NRE lidar scans across three domains, thus providing a novel challenge to existing semantic segmentation research upon this largely unexplored lidar modality. Finally, we propose, for the first time to the best of our knowledge, continuous-time ground truth based on optimization-based registration of lidar-inertial data on large survey-grade prior maps, which are also publicly released, each several times the size of existing ones. We conduct a rigorous evaluation of numerous state-of-the-art algorithms on MCD, report their performance, and highlight the challenges awaiting solutions from the research community. △ Less

Submitted 18 March, 2024; originally announced March 2024.

Comments: Accepted by The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024

DUFOMap: Efficient Dynamic Awareness Mapping

Authors: Daniel Duberg, Qingwen Zhang, MingKai Jia, Patric Jensfelt

Abstract: The dynamic nature of the real world is one of the main challenges in robotics. The first step in dealing with it is to detect which parts of the world are dynamic. A typical benchmark task is to create a map that contains only the static part of the world to support, for example, localization and planning. Current solutions are often applied in post-processing, where parameter tuning allows the u… ▽ More The dynamic nature of the real world is one of the main challenges in robotics. The first step in dealing with it is to detect which parts of the world are dynamic. A typical benchmark task is to create a map that contains only the static part of the world to support, for example, localization and planning. Current solutions are often applied in post-processing, where parameter tuning allows the user to adjust the setting for a specific dataset. In this paper, we propose DUFOMap, a novel dynamic awareness mapping framework designed for efficient online processing. Despite having the same parameter settings for all scenarios, it performs better or is on par with state-of-the-art methods. Ray casting is utilized to identify and classify fully observed empty regions. Since these regions have been observed empty, it follows that anything inside them at another time must be dynamic. Evaluation is carried out in various scenarios, including outdoor environments in KITTI and Argoverse 2, open areas on the KTH campus, and with different sensor types. DUFOMap outperforms the state of the art in terms of accuracy and computational efficiency. The source code, benchmarks, and links to the datasets utilized are provided. See https://kth-rpl.github.io/dufomap for more details. △ Less

Submitted 12 April, 2024; v1 submitted 3 March, 2024; originally announced March 2024.

Comments: The first two authors hold equal contribution. 8 pages, 7 figures, project page https://kth-rpl.github.io/dufomap

DeFlow: Decoder of Scene Flow Network in Autonomous Driving

Authors: Qingwen Zhang, Yi Yang, Heng Fang, Ruoyu Geng, Patric Jensfelt

Abstract: Scene flow estimation determines a scene's 3D motion field, by predicting the motion of points in the scene, especially for aiding tasks in autonomous driving. Many networks with large-scale point clouds as input use voxelization to create a pseudo-image for real-time running. However, the voxelization process often results in the loss of point-specific features. This gives rise to a challenge in… ▽ More Scene flow estimation determines a scene's 3D motion field, by predicting the motion of points in the scene, especially for aiding tasks in autonomous driving. Many networks with large-scale point clouds as input use voxelization to create a pseudo-image for real-time running. However, the voxelization process often results in the loss of point-specific features. This gives rise to a challenge in recovering those features for scene flow tasks. Our paper introduces DeFlow which enables a transition from voxel-based features to point features using Gated Recurrent Unit (GRU) refinement. To further enhance scene flow estimation performance, we formulate a novel loss function that accounts for the data imbalance between static and dynamic points. Evaluations on the Argoverse 2 scene flow task reveal that DeFlow achieves state-of-the-art results on large-scale point cloud data, demonstrating that our network has better performance and efficiency compared to others. The code is open-sourced at https://github.com/KTH-RPL/deflow. △ Less

Submitted 29 January, 2024; originally announced January 2024.

Comments: 7 pages, 4 figures, Code check https://github.com/KTH-RPL/deflow, accepted by ICRA 2024

Transitional Grid Maps: Joint Modeling of Static and Dynamic Occupancy

Authors: José Manuel Gaspar Sánchez, Leonard Bruns, Jana Tumova, Patric Jensfelt, Martin Törngren

Abstract: Autonomous agents rely on sensor data to construct representations of their environments, essential for predicting future events and planning their actions. However, sensor measurements suffer from limited range, occlusions, and sensor noise. These challenges become more evident in highly dynamic environments. This work proposes a probabilistic framework to jointly infer which parts of an environm… ▽ More Autonomous agents rely on sensor data to construct representations of their environments, essential for predicting future events and planning their actions. However, sensor measurements suffer from limited range, occlusions, and sensor noise. These challenges become more evident in highly dynamic environments. This work proposes a probabilistic framework to jointly infer which parts of an environment are statically and which parts are dynamically occupied. We formulate the problem as a Bayesian network and introduce minimal assumptions that significantly reduce the complexity of the problem. Based on those, we derive Transitional Grid Maps (TGMs), an efficient analytical solution. Using real data, we demonstrate how this approach produces better maps by keeping track of both static and dynamic elements and, as a side effect, can help improve existing SLAM algorithms. △ Less

Submitted 4 November, 2024; v1 submitted 12 January, 2024; originally announced January 2024.

Towards Long-Range 3D Object Detection for Autonomous Vehicles

Authors: Ajinkya Khoche, Laura Pereira Sánchez, Nazre Batool, Sina Sharif Mansouri, Patric Jensfelt

Abstract: 3D object detection at long range is crucial for ensuring the safety and efficiency of self driving vehicles, allowing them to accurately perceive and react to objects, obstacles, and potential hazards from a distance. But most current state of the art LiDAR based methods are range limited due to sparsity at long range, which generates a form of domain gap between points closer to and farther away… ▽ More 3D object detection at long range is crucial for ensuring the safety and efficiency of self driving vehicles, allowing them to accurately perceive and react to objects, obstacles, and potential hazards from a distance. But most current state of the art LiDAR based methods are range limited due to sparsity at long range, which generates a form of domain gap between points closer to and farther away from the ego vehicle. Another related problem is the label imbalance for faraway objects, which inhibits the performance of Deep Neural Networks at long range. To address the above limitations, we investigate two ways to improve long range performance of current LiDAR based 3D detectors. First, we combine two 3D detection networks, referred to as range experts, one specializing at near to mid range objects, and one at long range 3D detection. To train a detector at long range under a scarce label regime, we further weigh the loss according to the labelled point's distance from ego vehicle. Second, we augment LiDAR scans with virtual points generated using Multimodal Virtual Points (MVP), a readily available image-based depth completion algorithm. Our experiments on the long range Argoverse2 (AV2) dataset indicate that MVP is more effective in improving long range performance, while maintaining a straightforward implementation. On the other hand, the range experts offer a computationally efficient and simpler alternative, avoiding dependency on image-based segmentation networks and perfect camera-LiDAR calibration. △ Less

Submitted 20 May, 2024; v1 submitted 7 October, 2023; originally announced October 2023.

Comments: Accepted to Intelligent Vehicle Symposium (IV) 2024

A Dynamic Points Removal Benchmark in Point Cloud Maps

Authors: Qingwen Zhang, Daniel Duberg, Ruoyu Geng, Mingkai Jia, Lujia Wang, Patric Jensfelt

Abstract: In the field of robotics, the point cloud has become an essential map representation. From the perspective of downstream tasks like localization and global path planning, points corresponding to dynamic objects will adversely affect their performance. Existing methods for removing dynamic points in point clouds often lack clarity in comparative evaluations and comprehensive analysis. Therefore, we… ▽ More In the field of robotics, the point cloud has become an essential map representation. From the perspective of downstream tasks like localization and global path planning, points corresponding to dynamic objects will adversely affect their performance. Existing methods for removing dynamic points in point clouds often lack clarity in comparative evaluations and comprehensive analysis. Therefore, we propose an easy-to-extend unified benchmarking framework for evaluating techniques for removing dynamic points in maps. It includes refactored state-of-art methods and novel metrics to analyze the limitations of these approaches. This enables researchers to dive deep into the underlying reasons behind these limitations. The benchmark makes use of several datasets with different sensor types. All the code and datasets related to our study are publicly available for further development and utilization. △ Less

Submitted 14 July, 2023; originally announced July 2023.

Comments: Code check https://github.com/KTH-RPL/DynamicMap_Benchmark.git , 7 pages, accepted by ITSC 2023

Happily Error After: Framework Development and User Study for Correcting Robot Perception Errors in Virtual Reality

Authors: Maciej K. Wozniak, Rebecca Stower, Patric Jensfelt, Andre Pereira

Abstract: While we can see robots in more areas of our lives, they still make errors. One common cause of failure stems from the robot perception module when detecting objects. Allowing users to correct such errors can help improve the interaction and prevent the same errors in the future. Consequently, we investigate the effectiveness of a virtual reality (VR) framework for correcting perception errors of… ▽ More While we can see robots in more areas of our lives, they still make errors. One common cause of failure stems from the robot perception module when detecting objects. Allowing users to correct such errors can help improve the interaction and prevent the same errors in the future. Consequently, we investigate the effectiveness of a virtual reality (VR) framework for correcting perception errors of a Franka Panda robot. We conducted a user study with 56 participants who interacted with the robot using both VR and screen interfaces. Participants learned to collaborate with the robot faster in the VR interface compared to the screen interface. Additionally, participants found the VR interface more immersive, enjoyable, and expressed a preference for using it again. These findings suggest that VR interfaces may offer advantages over screen interfaces for human-robot interaction in erroneous environments. △ Less

Submitted 26 June, 2023; originally announced June 2023.

Comments: Accepted for IEEE RO-MAN 2023

Towards a Robust Sensor Fusion Step for 3D Object Detection on Corrupted Data

Authors: Maciej K. Wozniak, Viktor Karefjards, Marko Thiel, Patric Jensfelt

Abstract: Multimodal sensor fusion methods for 3D object detection have been revolutionizing the autonomous driving research field. Nevertheless, most of these methods heavily rely on dense LiDAR data and accurately calibrated sensors which is often not the case in real-world scenarios. Data from LiDAR and cameras often come misaligned due to the miscalibration, decalibration, or different frequencies of th… ▽ More Multimodal sensor fusion methods for 3D object detection have been revolutionizing the autonomous driving research field. Nevertheless, most of these methods heavily rely on dense LiDAR data and accurately calibrated sensors which is often not the case in real-world scenarios. Data from LiDAR and cameras often come misaligned due to the miscalibration, decalibration, or different frequencies of the sensors. Additionally, some parts of the LiDAR data may be occluded and parts of the data may be missing due to hardware malfunction or weather conditions. This work presents a novel fusion step that addresses data corruptions and makes sensor fusion for 3D object detection more robust. Through extensive experiments, we demonstrate that our method performs on par with state-of-the-art approaches on normal data and outperforms them on misaligned data. △ Less

Submitted 12 June, 2023; originally announced June 2023.

RGB-D-Based Categorical Object Pose and Shape Estimation: Methods, Datasets, and Evaluation

Authors: Leonard Bruns, Patric Jensfelt

Abstract: Recently, various methods for 6D pose and shape estimation of objects at a per-category level have been proposed. This work provides an overview of the field in terms of methods, datasets, and evaluation protocols. First, an overview of existing works and their commonalities and differences is provided. Second, we take a critical look at the predominant evaluation protocol, including metrics and d… ▽ More Recently, various methods for 6D pose and shape estimation of objects at a per-category level have been proposed. This work provides an overview of the field in terms of methods, datasets, and evaluation protocols. First, an overview of existing works and their commonalities and differences is provided. Second, we take a critical look at the predominant evaluation protocol, including metrics and datasets. Based on the findings, we propose a new set of metrics, contribute new annotations for the Redwood dataset, and evaluate state-of-the-art methods in a fair comparison. The results indicate that existing methods do not generalize well to unconstrained orientations and are actually heavily biased towards objects being upright. We provide an easy-to-use evaluation toolbox with well-defined metrics, methods, and dataset interfaces, which allows evaluation and comparison with various state-of-the-art approaches (https://github.com/roym899/pose_and_shape_evaluation). △ Less

Submitted 19 January, 2023; originally announced January 2023.

Comments: arXiv admin note: substantial text overlap with arXiv:2202.10346

What you see is (not) what you get: A VR Framework for Correcting Robot Errors

Authors: Maciej K. Wozniak, Rebecca Stower, Patric Jensfelt, Andre Pereira

Abstract: Many solutions tailored for intuitive visualization or teleoperation of virtual, augmented and mixed (VAM) reality systems are not robust to robot failures, such as the inability to detect and recognize objects in the environment or planning unsafe trajectories. In this paper, we present a novel virtual reality (VR) framework where users can (i) recognize when the robot has failed to detect a real… ▽ More Many solutions tailored for intuitive visualization or teleoperation of virtual, augmented and mixed (VAM) reality systems are not robust to robot failures, such as the inability to detect and recognize objects in the environment or planning unsafe trajectories. In this paper, we present a novel virtual reality (VR) framework where users can (i) recognize when the robot has failed to detect a real-world object, (ii) correct the error in VR, (iii) modify proposed object trajectories and, (iv) implement behaviors on a real-world robot. Finally, we propose a user study aimed at testing the efficacy of our framework. Project materials can be found in the OSF repository. △ Less

Submitted 17 January, 2023; v1 submitted 12 January, 2023; originally announced January 2023.

Journal ref: HRI '23: Companion of the 2023 ACM/IEEE International Conference on Human-Robot Interaction

A Probabilistic Framework for Visual Localization in Ambiguous Scenes

Authors: Fereidoon Zangeneh, Leonard Bruns, Amit Dekel, Alessandro Pieropan, Patric Jensfelt

Abstract: Visual localization allows autonomous robots to relocalize when losing track of their pose by matching their current observation with past ones. However, ambiguous scenes pose a challenge for such systems, as repetitive structures can be viewed from many distinct, equally likely camera poses, which means it is not sufficient to produce a single best pose hypothesis. In this work, we propose a prob… ▽ More Visual localization allows autonomous robots to relocalize when losing track of their pose by matching their current observation with past ones. However, ambiguous scenes pose a challenge for such systems, as repetitive structures can be viewed from many distinct, equally likely camera poses, which means it is not sufficient to produce a single best pose hypothesis. In this work, we propose a probabilistic framework that for a given image predicts the arbitrarily shaped posterior distribution of its camera pose. We do this via a novel formulation of camera pose regression using variational inference, which allows sampling from the predicted distribution. Our method outperforms existing methods on localization in ambiguous scenes. Code and data will be released at https://github.com/efreidun/vapor. △ Less

Submitted 5 January, 2023; originally announced January 2023.

SLICT: Multi-input Multi-scale Surfel-Based Lidar-Inertial Continuous-Time Odometry and Mapping

Authors: Thien-Minh Nguyen, Daniel Duberg, Patric Jensfelt, Shenghai Yuan, Lihua Xie

Abstract: While feature association to a global map has significant benefits, to keep the computations from growing exponentially, most lidar-based odometry and mapping methods opt to associate features with local maps at one voxel scale. Taking advantage of the fact that surfels (surface elements) at different voxel scales can be organized in a tree-like structure, we propose an octree-based global map of… ▽ More While feature association to a global map has significant benefits, to keep the computations from growing exponentially, most lidar-based odometry and mapping methods opt to associate features with local maps at one voxel scale. Taking advantage of the fact that surfels (surface elements) at different voxel scales can be organized in a tree-like structure, we propose an octree-based global map of multi-scale surfels that can be updated incrementally. This alleviates the need for recalculating, for example, a k-d tree of the whole map repeatedly. The system can also take input from a single or a number of sensors, reinforcing the robustness in degenerate cases. We also propose a point-to-surfel (PTS) association scheme, continuous-time optimization on PTS and IMU preintegration factors, along with loop closure and bundle adjustment, making a complete framework for Lidar-Inertial continuous-time odometry and mapping. Experiments on public and in-house datasets demonstrate the advantages of our system compared to other state-of-the-art methods. To benefit the community, we release the source code and dataset at https://github.com/brytsknguyen/slict. △ Less

Submitted 9 November, 2022; v1 submitted 7 November, 2022; originally announced November 2022.

Semantic 3D Grid Maps for Autonomous Driving

Authors: Ajinkya Khoche, Maciej K Wozniak, Daniel Duberg, Patric Jensfelt

Abstract: Maps play a key role in rapidly developing area of autonomous driving. We survey the literature for different map representations and find that while the world is three-dimensional, it is common to rely on 2D map representations in order to meet real-time constraints. We believe that high levels of situation awareness require a 3D representation as well as the inclusion of semantic information. We… ▽ More Maps play a key role in rapidly developing area of autonomous driving. We survey the literature for different map representations and find that while the world is three-dimensional, it is common to rely on 2D map representations in order to meet real-time constraints. We believe that high levels of situation awareness require a 3D representation as well as the inclusion of semantic information. We demonstrate that our recently presented hierarchical 3D grid mapping framework UFOMap meets the real-time constraints. Furthermore, we show how it can be used to efficiently support more complex functions such as calculating the occluded parts of space and accumulating the output from a semantic segmentation network. △ Less

Submitted 9 November, 2022; v1 submitted 3 November, 2022; originally announced November 2022.

Comments: Submitted, accepted and presented at the 25th IEEE International Conference on Intelligent Transportation Systems (IEEE ITSC 2022)

SDFEst: Categorical Pose and Shape Estimation of Objects from RGB-D using Signed Distance Fields

Authors: Leonard Bruns, Patric Jensfelt

Abstract: Rich geometric understanding of the world is an important component of many robotic applications such as planning and manipulation. In this paper, we present a modular pipeline for pose and shape estimation of objects from RGB-D images given their category. The core of our method is a generative shape model, which we integrate with a novel initialization network and a differentiable renderer to en… ▽ More Rich geometric understanding of the world is an important component of many robotic applications such as planning and manipulation. In this paper, we present a modular pipeline for pose and shape estimation of objects from RGB-D images given their category. The core of our method is a generative shape model, which we integrate with a novel initialization network and a differentiable renderer to enable 6D pose and shape estimation from a single or multiple views. We investigate the use of discretized signed distance fields as an efficient shape representation for fast analysis-by-synthesis optimization. Our modular framework enables multi-view optimization and extensibility. We demonstrate the benefits of our approach over state-of-the-art methods in several experiments on both synthetic and real data. We open-source our approach at https://github.com/roym899/sdfest. △ Less

Submitted 11 July, 2022; originally announced July 2022.

Comments: Accepted to IEEE Robotics and Automation Letters (and IROS 2022). Project page: https://github.com/roym899/sdfest

SDF-based RGB-D Camera Tracking in Neural Scene Representations

Authors: Leonard Bruns, Fereidoon Zangeneh, Patric Jensfelt

Abstract: We consider the problem of tracking the 6D pose of a moving RGB-D camera in a neural scene representation. Different such representations have recently emerged, and we investigate the suitability of them for the task of camera tracking. In particular, we propose to track an RGB-D camera using a signed distance field-based representation and show that compared to density-based representations, trac… ▽ More We consider the problem of tracking the 6D pose of a moving RGB-D camera in a neural scene representation. Different such representations have recently emerged, and we investigate the suitability of them for the task of camera tracking. In particular, we propose to track an RGB-D camera using a signed distance field-based representation and show that compared to density-based representations, tracking can be sped up, which enables more robust and accurate pose estimates when computation time is limited. △ Less

Submitted 4 May, 2022; originally announced May 2022.

Comments: Accepted to the "Motion Planning with Implicit Neural Representations of Geometry" Workshop at ICRA 2022

FloorGenT: Generative Vector Graphic Model of Floor Plans for Robotics

Authors: Ludvig Ericson, Patric Jensfelt

Abstract: Floor plans are the basis of reasoning in and communicating about indoor environments. In this paper, we show that by modelling floor plans as sequences of line segments seen from a particular point of view, recent advances in autoregressive sequence modelling can be leveraged to model and predict floor plans. The line segments are canonicalized and translated to sequence of tokens and an attentio… ▽ More Floor plans are the basis of reasoning in and communicating about indoor environments. In this paper, we show that by modelling floor plans as sequences of line segments seen from a particular point of view, recent advances in autoregressive sequence modelling can be leveraged to model and predict floor plans. The line segments are canonicalized and translated to sequence of tokens and an attention-based neural network is used to fit a one-step distribution over next tokens. We fit the network to sequences derived from a set of large-scale floor plans, and demonstrate the capabilities of the model in four scenarios: novel floor plan generation, completion of partially observed floor plans, generation of floor plans from simulated sensor data, and finally, the applicability of a floor plan model in predicting the shortest distance with partial knowledge of the environment. △ Less

Submitted 7 March, 2022; originally announced March 2022.

Comments: Submitted to IROS 2022. 7 pages, 6 figures

On the Evaluation of RGB-D-based Categorical Pose and Shape Estimation

Authors: Leonard Bruns, Patric Jensfelt

Abstract: Recently, various methods for 6D pose and shape estimation of objects have been proposed. Typically, these methods evaluate their pose estimation in terms of average precision, and reconstruction quality with chamfer distance. In this work we take a critical look at this predominant evaluation protocol including metrics and datasets. We propose a new set of metrics, contribute new annotations for… ▽ More Recently, various methods for 6D pose and shape estimation of objects have been proposed. Typically, these methods evaluate their pose estimation in terms of average precision, and reconstruction quality with chamfer distance. In this work we take a critical look at this predominant evaluation protocol including metrics and datasets. We propose a new set of metrics, contribute new annotations for the Redwood dataset and evaluate state-of-the-art methods in a fair comparison. We find that existing methods do not generalize well to unconstrained orientations, and are actually heavily biased towards objects being upright. We contribute an easy-to-use evaluation toolbox with well-defined metrics, method and dataset interfaces, which readily allows evaluation and comparison with various state-of-the-art approaches (see https://github.com/roym899/pose_and_shape_evaluation ). △ Less

Submitted 21 February, 2022; originally announced February 2022.

Comments: 17 pages, 8 figures, submitted to IAS-17

UFOMap: An Efficient Probabilistic 3D Mapping Framework That Embraces the Unknown

Authors: Daniel Duberg, Patric Jensfelt

Abstract: 3D models are an essential part of many robotic applications. In applications where the environment is unknown a-priori, or where only a part of the environment is known, it is important that the 3D model can handle the unknown space efficiently. Path planning, exploration, and reconstruction all fall into this category. In this paper we present an extension to OctoMap which we call UFOMap. UFOMap… ▽ More 3D models are an essential part of many robotic applications. In applications where the environment is unknown a-priori, or where only a part of the environment is known, it is important that the 3D model can handle the unknown space efficiently. Path planning, exploration, and reconstruction all fall into this category. In this paper we present an extension to OctoMap which we call UFOMap. UFOMap uses an explicit representation of all three states in the map, i.e., occupied, free, and unknown. This gives, surprisingly, a more memory efficient representation. Furthermore, we provide methods that allow for significantly faster insertions into the octree. This enables real-time colored volumetric mapping at high resolution (below 1 cm). UFOMap is contributed as a C++ library that can be used standalone but is also integrated into ROS. △ Less

Submitted 10 March, 2020; originally announced March 2020.

Comments: Project page: https://github.com/danielduberg/UFOMap

Self-Supervised 3D Keypoint Learning for Ego-motion Estimation

Authors: Jiexiong Tang, Rares Ambrus, Vitor Guizilini, Sudeep Pillai, Hanme Kim, Patric Jensfelt, Adrien Gaidon

Abstract: Detecting and matching robust viewpoint-invariant keypoints is critical for visual SLAM and Structure-from-Motion. State-of-the-art learning-based methods generate training samples via homography adaptation to create 2D synthetic views with known keypoint matches from a single image. This approach, however, does not generalize to non-planar 3D scenes with illumination variations commonly seen in r… ▽ More Detecting and matching robust viewpoint-invariant keypoints is critical for visual SLAM and Structure-from-Motion. State-of-the-art learning-based methods generate training samples via homography adaptation to create 2D synthetic views with known keypoint matches from a single image. This approach, however, does not generalize to non-planar 3D scenes with illumination variations commonly seen in real-world videos. In this work, we propose self-supervised learning of depth-aware keypoints directly from unlabeled videos. We jointly learn keypoint and depth estimation networks by combining appearance and geometric matching via a differentiable structure-from-motion module based on Procrustean residual pose correction. We describe how our self-supervised keypoints can be integrated into state-of-the-art visual odometry frameworks for robust and accurate ego-motion estimation of autonomous vehicles in real-world conditions. △ Less

Submitted 17 November, 2020; v1 submitted 6 December, 2019; originally announced December 2019.

Flexible Disaster Response of Tomorrow -- Final Presentation and Evaluation of the CENTAURO System

Authors: Tobias Klamt, Diego Rodriguez, Lorenzo Baccelliere, Xi Chen, Domenico Chiaradia, Torben Cichon, Massimiliano Gabardi, Paolo Guria, Karl Holmquist, Malgorzata Kamedula, Hakan Karaoguz, Navvab Kashiri, Arturo Laurenzi, Christian Lenz, Daniele Leonardis, Enrico Mingo Hoffman, Luca Muratore, Dmytro Pavlichenko, Francesco Porcini, Zeyu Ren, Fabian Schilling, Max Schwarz, Massimiliano Solazzi, Michael Felsberg, Antonio Frisoli , et al. (7 additional authors not shown)

Abstract: Mobile manipulation robots have high potential to support rescue forces in disaster-response missions. Despite the difficulties imposed by real-world scenarios, robots are promising to perform mission tasks from a safe distance. In the CENTAURO project, we developed a disaster-response system which consists of the highly flexible Centauro robot and suitable control interfaces including an immersiv… ▽ More Mobile manipulation robots have high potential to support rescue forces in disaster-response missions. Despite the difficulties imposed by real-world scenarios, robots are promising to perform mission tasks from a safe distance. In the CENTAURO project, we developed a disaster-response system which consists of the highly flexible Centauro robot and suitable control interfaces including an immersive tele-presence suit and support-operator controls on different levels of autonomy. In this article, we give an overview of the final CENTAURO system. In particular, we explain several high-level design decisions and how those were derived from requirements and extensive experience of Kerntechnische Hilfsdienst GmbH, Karlsruhe, Germany (KHG). We focus on components which were recently integrated and report about a systematic evaluation which demonstrated system capabilities and revealed valuable insights. △ Less

Submitted 19 September, 2019; originally announced September 2019.

Comments: Accepted for IEEE Robotics and Automation Magazine (RAM), to appear December 2019

Adversarial Feature Training for Generalizable Robotic Visuomotor Control

Authors: Xi Chen, Ali Ghadirzadeh, Mårten Björkman, Patric Jensfelt

Abstract: Deep reinforcement learning (RL) has enabled training action-selection policies, end-to-end, by learning a function which maps image pixels to action outputs. However, it's application to visuomotor robotic policy training has been limited because of the challenge of large-scale data collection when working with physical hardware. A suitable visuomotor policy should perform well not just for the t… ▽ More Deep reinforcement learning (RL) has enabled training action-selection policies, end-to-end, by learning a function which maps image pixels to action outputs. However, it's application to visuomotor robotic policy training has been limited because of the challenge of large-scale data collection when working with physical hardware. A suitable visuomotor policy should perform well not just for the task-setup it has been trained for, but also for all varieties of the task, including novel objects at different viewpoints surrounded by task-irrelevant objects. However, it is impractical for a robotic setup to sufficiently collect interactive samples in a RL framework to generalize well to novel aspects of a task. In this work, we demonstrate that by using adversarial training for domain transfer, it is possible to train visuomotor policies based on RL frameworks, and then transfer the acquired policy to other novel task domains. We propose to leverage the deep RL capabilities to learn complex visuomotor skills for uncomplicated task setups, and then exploit transfer learning to generalize to new task domains provided only still images of the task in the target domain. We evaluate our method on two real robotic tasks, picking and pouring, and compare it to a number of prior works, demonstrating its superiority. △ Less

Submitted 17 September, 2019; originally announced September 2019.