Abhinav Valada

University of Freiburg

収録論文 138本 ・ フィジカルAI/ロボット学習

※arXiv著者名で収集。同姓同名の別人の論文が含まれる場合があります。

論文

• 行動から注意を学ぶ：ポリシー学習のための創発的視覚ボトルネック
  視覚的注意/ポリシー学習2026/8/13

  行動教師信号のみから注目領域（ROI）を学習するSeekerを提案し、RGBクロップや点群フィルタリングの空間インターフェースとして利用。実機で成功率を大幅に向上させた。

• ケアロボットに関する人間中心の考察：介護者の視点の比較研究
  ケアロボット2026/8/3

  米国、メキシコ、チリの介護者298人を対象に、4種類のケアロボット（物品搬送、ベッド移動補助、バイタルサイン監視、移動支援）に対する認識を混合手法で調査し、国を超えて概ね肯定的な評価が得られた一方、倫理的懸念（依存性、人間の監督、雇用への影響）も明らかにした。

• Human-Centered Reflections on Care Robots: A Comparative Study of Caregiver Perspectives
  2026/8/1
• Attention from Action, for Action: Emergent Visual Bottlenecks for Policy Learning
  2026/8/1
• One Hand Watches The Other: Dynamic Multi-Agent Cooperation for Sample-Efficient Bimanual Manipulation in Dynamic Environments
  2026/7/1
• Streaming Gaussian Encoding for 4D Panoptic Occupancy Tracking
  2026/6/1
• CoPark: Learning Reactive Parking via Self-Play
  2026/6/1
• Sensor Configuration Matters: A Systematic Evaluation of Multimodal SLAM on Quadruped Robots
  2026/6/1
• 3D Scene Graphs: Open Challenges and Future Directions
  2026/6/1
• AnchorD: Metric Grounding of Monocular Depth Using Factor Graphs
  2026/5/1
• Self-Supervised Online Robot-Agnostic Traversability Estimation for Open-World Environments
  2026/5/1
• Hyp2Former: Hierarchy-Aware Hyperbolic Embeddings for Open-Set Panoptic Segmentation
  2026/5/1
• Leveraging Previous-Traversal Point Cloud Map Priors for Camera-Based 3D Object Detection and Tracking
  2026/4/1
• Class-Incremental Motion Forecasting
  2026/3/1
• Effort-Based Criticality Metrics for Evaluating 3D Perception Errors in Autonomous Driving
  2026/3/1
• The Neural Compass: Probabilistic Relative Feature Fields for Robotic Search
  2026/3/1
• Sparse3DTrack: Monocular 3D Object Tracking Using Sparse Supervision
  2026/3/1
• Spectral Alignment in Forward-Backward Representations via Temporal Abstraction
  2026/3/1
• Relational Semantic Reasoning on 3D Scene Graphs for Open World Interactive Object Search
  2026/3/1
• LAD-Drive: Bridging Language and Trajectory with Action-Aware Diffusion Transformers
  2026/3/1
• SparTa: Sparse Graphical Task Models from a Handful of Demonstrations
  2026/2/1
• ParkDiffusion++: Ego Intention Conditioned Joint Multi-Agent Trajectory Prediction for Automated Parking using Diffusion Models
  2026/2/1
• Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking
  2026/2/1
• Articulated 3D Scene Graphs for Open-World Mobile Manipulation
  2026/2/1
• Scaling Single Human Demonstrations for Imitation Learning using Generative Foundational Models
  2026/2/1
• ForecastOcc: Vision-based Semantic Occupancy Forecasting
  2026/2/1
• Online Estimation and Manipulation of Articulated Objects
  2026/1/1
• Hoi! - A Multimodal Dataset for Force-Grounded, Cross-View Articulated Manipulation
  2025/12/1
• Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Tracking
  2025/10/1
• Preference-Based Long-Horizon Robotic Stacking with Multimodal Large Language Models
  2025/9/1
• Hyperspectral Adapter for Semantic Segmentation with Vision Foundation Models
  2025/9/1
• MSG: Multi-Stream Generative Policies for Sample-Efficient Robotic Manipulation
  2025/9/1
• Articulated Object Estimation in the Wild
  2025/9/1
• DiWA: Diffusion Policy Adaptation with World Models
  2025/8/1
• Dynamic Robot-Assisted Surgery with Hierarchical Class-Incremental Semantic Segmentation
  2025/8/1
• Designing for Difference: How Human Characteristics Shape Perceptions of Collaborative Robots
  2025/7/1
• cVLA: Towards Efficient Camera-Space VLAs
  2025/7/1
• Open-Set LiDAR Panoptic Segmentation Guided by Uncertainty-Aware Learning
  2025/6/1
• Visual Loop Closure Detection Through Deep Graph Consensus
  2025/5/1
• ParkDiffusion: Heterogeneous Multi-Agent Multi-Modal Trajectory Prediction for Automated Parking using Diffusion Models
  2025/5/1
• The Unreasonable Effectiveness of Discrete-Time Gaussian Process Mixtures for Robot Policy Learning
  2025/5/1
• MORE: Mobile Manipulation Rearrangement Through Grounded Language Reasoning
  2025/5/1
• Robotic Task Ambiguity Resolution via Natural Language Interaction
  2025/4/1
• Label-Efficient LiDAR Panoptic Segmentation
  2025/3/1
• OpenLex3D: A Tiered Evaluation Benchmark for Open-Vocabulary 3D Scene Representations
  2025/3/1
• Evidential Uncertainty Estimation for Multi-Modal Trajectory Prediction
  2025/3/1
• Learning Appearance and Motion Cues for Panoptic Tracking
  2025/3/1
• Collaborative Dynamic 3D Scene Graphs for Open-Vocabulary Urban Scene Understanding
  2025/3/1
• Multi-Scale Neighborhood Occupancy Masked Autoencoder for Self-Supervised Learning in LiDAR Point Clouds
  2025/2/1
• Task-Driven Co-Design of Mobile Manipulators
  2024/12/1
• The Bare Necessities: Designing Simple, Effective Open-Vocabulary Scene Graphs
  2024/12/1
• ROVER: A Multi-Season Dataset for Visual SLAM
  2024/12/1
• NeRF and Gaussian Splatting SLAM in the Wild
  2024/12/1
• Traffic and Safety Rule Compliance of Humans in Diverse Driving Situations
  2024/11/1
• Efficient Learning of Object Placement with Intra-Category Transfer
  2024/11/1
• Neural Fields in Robotics: A Survey
  2024/10/1
• Stochasticity in Motion: An Information-Theoretic Approach to Trajectory Prediction
  2024/10/1
• Whole-Body Teleoperation for Mobile Manipulation at Zero Added Cost
  2024/9/1
• Panoptic-Depth Forecasting
  2024/9/1
• Learning Robotic Manipulation Policies from Point Clouds with Conditional Flow Matching
  2024/9/1
• Motion Forecasting via Model-Based Risk Minimization
  2024/9/1
• Visual-Inertial SLAM for Unstructured Outdoor Environments: Benchmarking the Benefits and Computational Costs of Loop Closing
  2024/8/1
• Perception Matters: Enhancing Embodied AI with Uncertainty-Aware Semantic Segmentation
  2024/8/1
• The Art of Imitation: Learning Long-Horizon Manipulation Tasks from Few Demonstrations
  2024/7/1
• Learning Lane Graphs from Aerial Imagery Using Transformers
  2024/7/1
• Taxonomy-Aware Continual Semantic Segmentation in Hyperbolic Spaces for Open-World Perception
  2024/7/1
• LetsMap: Unsupervised Representation Learning for Semantic BEV Mapping
  2024/5/1
• A Good Foundation is Worth Many Labels: Label-Efficient Panoptic Segmentation
  2024/5/1
• Imagine2touch: Predictive Tactile Sensing for Robotic Manipulation using Efficient Low-Dimensional Signals
  2024/5/1
• Automatic Target-Less Camera-LiDAR Calibration From Motion and Deep Point Correspondences
  2024/4/1
• CenterArt: Joint Shape Reconstruction and 6-DoF Grasp Estimation of Articulated Objects
  2024/4/1
• Bayesian Optimization for Sample-Efficient Policy Improvement in Robotic Manipulation
  2024/3/1
• Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation
  2024/3/1
• Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation
  2024/3/1
• PseudoTouch: Efficiently Imaging the Surface Feel of Objects for Robotic Manipulation
  2024/3/1
• DITTO: Demonstration Imitation by Trajectory Transformation
  2024/3/1
• BEVCar: Camera-Radar Fusion for BEV Map and Object Segmentation
  2024/3/1
• Evaluation of a Smart Mobile Robotic System for Industrial Plant Inspection and Supervision
  2024/2/1
• CMRNext: Camera to LiDAR Matching in the Wild for Localization and Extrinsic Calibration
  2024/2/1
• Semantic Scene Segmentation for Robotics
  2024/1/1
• CenterGrasp: Object-Aware Implicit Representation Learning for Simultaneous Shape Reconstruction and 6-DoF Grasp Estimation
  2023/12/1
• Amodal Optical Flow
  2023/11/1
• Compositional Servoing by Recombining Demonstrations
  2023/10/1
• Few-Shot Panoptic Segmentation With Foundation Models
  2023/9/1
• Collaborative Dynamic 3D Scene Graphs for Automated Driving
  2023/9/1
• Multi-camera Bird's Eye View Perception for Autonomous Driving
  2023/9/1
• RaLF: Flow-based Global and Metric Radar Localization in LiDAR Maps
  2023/9/1
• Online Estimation of Articulated Objects with Factor Graphs using Vision and Proprioceptive Sensing
  2023/9/1
• A Smart Robotic System for Industrial Plant Supervision
  2023/8/1
• Learning Hierarchical Interactive Multi-Object Search for Mobile Manipulation
  2023/7/1
• Efficient Learning of Urban Driving Policies Using Bird's-Eye-View State Representations
  2023/5/1
• The Treachery of Images: Bayesian Scene Keypoints for Deep Policy Learning in Robotic Manipulation
  2023/5/1
• CoVIO: Online Continual Learning for Visual-Inertial Odometry
  2023/3/1
• CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects
  2023/3/1
• CoDEPS: Online Continual Learning for Depth Estimation and Panoptic Segmentation
  2023/3/1
• INoD: Injected Noise Discriminator for Self-Supervised Representation Learning in Agricultural Fields
  2023/3/1
• SkyEye: Self-Supervised Bird's-Eye-View Semantic Mapping Using Monocular Frontal View Images
  2023/2/1
• Learning and Aggregating Lane Graphs for Urban Automated Driving
  2023/2/1
• Interactive Imitation Learning in Robotics: A Survey
  2022/11/1
• Active Particle Filter Networks: Efficient Active Localization in Continuous Action Spaces and Large Maps
  2022/9/1
• PADLoC: LiDAR-Based Deep Loop Closure Detection and Registration Using Panoptic Attention
  2022/9/1
• RobotIO: A Python Library for Robot Manipulation Experiments
  2022/7/1
• Fairness and Bias in Robot Learning
  2022/7/1
• N$^2$M$^2$: Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environments
  2022/6/1
• Learning Long-Horizon Robot Exploration Strategies for Multi-Object Search in Continuous Action Spaces
  2022/5/1
• Perceiving the Invisible: Proposal-Free Amodal Panoptic Segmentation
  2022/5/1
• Self-Supervised Learning of Multi-Object Keypoints for Robotic Manipulation
  2022/5/1
• 3D Multi-Object Tracking Using Graph Neural Networks with Cross-Edge Modality Attention
  2022/3/1
• Continual SLAM: Beyond Lifelong Simultaneous Localization and Mapping Through Continual Learning
  2022/3/1
• Amodal Panoptic Segmentation
  2022/2/1
• Doing Right by Not Doing Wrong in Human-Robot Collaboration
  2022/2/1
• 7th AI Driving Olympics: 1st Place Report for Panoptic Tracking
  2021/12/1
• Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Sounds
  2021/11/1
• Robot Skill Adaptation via Soft Actor-Critic Gaussian Mixture Models
  2021/11/1
• Correct Me if I am Wrong: Interactive Learning for Robotic Manipulation
  2021/10/1
• Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking
  2021/9/1
• Unsupervised Domain Adaptation for LiDAR Panoptic Segmentation
  2021/9/1
• Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View Images
  2021/8/1
• Multi-Perspective Anomaly Detection
  2021/5/1
• LCDNet: Deep Loop Closure Detection and Point Cloud Registration for LiDAR SLAM
  2021/3/1
• There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge
  2021/3/1
• EfficientLPS: Efficient LiDAR Panoptic Segmentation
  2021/2/1
• Learning Kinematic Feasibility for Mobile Manipulation through Deep Reinforcement Learning
  2021/1/1
• From Learning to Relearning: A Framework for Diminishing Bias in Social Robot Navigation
  2021/1/1
• Kineverse: A Symbolic Articulation Model Framework for Model-Agnostic Mobile Manipulation
  2020/12/1
• Robust Vision Challenge 2020 -- 1st Place Report for Panoptic Segmentation
  2020/8/1
• Dynamic Object Removal and Spatio-Temporal RGB-D Inpainting via Geometry-Aware Adversarial Learning
  2020/8/1
• EfficientPS: Efficient Panoptic Segmentation
  2020/4/1
• CMRNet++: Map and Camera Agnostic Monocular Visual Localization in LiDAR Maps
  2020/4/1
• MOPT: Multi-Object Panoptic Tracking
  2020/4/1
• Self-Supervised Visual Terrain Classification from Unsupervised Acoustic Feature Learning
  2019/12/1
• Vision-Based Autonomous UAV Navigation and Landing for Urban Search and Rescue
  2019/6/1
• Robot Localization in Floor Plans Using a Room Layout Edge Extraction Network
  2019/3/1
• Vision-based Autonomous Landing in Catastrophe-Struck Environments
  2018/9/1
• Multimodal Interaction-aware Motion Prediction for Autonomous Street Crossing
  2018/8/1
• VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometry
  2018/4/1
• Deep Spatiotemporal Models for Robust Proprioceptive Terrain Classification
  2018/4/1
• Deep Auxiliary Learning for Visual Localization and Odometry
  2018/3/1