Dieter Fox
University of Washington
収録論文 210本 ・ フィジカルAI/ロボット学習
VLA
※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
- Flex-π: 計算柔軟性を備えたマルチストリーム世界行動モデルVLA2026/8/11
凍結したビデオ生成VAEが3D点群も符号化できることを発見し、RGBに加えて3D幾何学と物体意味論を共同で学習する世界行動モデルを提案。推論時にストリームを選択可能で、実世界の両腕操作タスクで高い性能を達成。
- Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility2026/8/1
- SeeTraceAct: Visibility-Aware Latent Planning from Cross-Embodiment Demonstration Videos2026/6/1
- TAM: Torque Adaptation Module for Robust Motion Transfer in Manipulation2026/6/1
- SeeTraceAct: Visibility-Aware Latent Planning from Cross-Embodiment Demonstration Videos2026/6/1
- MolmoAct2: Action Reasoning Models for Real-world Deployment2026/5/1
- RoboPlayground: Democratizing Robotic Evaluation through Structured Physical Domains2026/4/1
- MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation2026/3/1
- Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons2026/3/1
- Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning2026/2/1
- TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics2026/2/1
- MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation2026/2/1
- PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation2026/1/1
- Point Bridge: 3D Representations for Cross Domain Policy Learning2026/1/1
- VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuning2025/10/1
- FailSafe: Reasoning and Recovery from Failures in Vision-Language-Action Models2025/10/1
- Refinery: Active Fine-tuning and Deployment-time Optimization for Contact-Rich Policies2025/10/1
- The Reality Gap in Robotics: Challenges, Solutions, and Best Practices2025/10/1
- PEEK: Guiding and Minimal Image Representations for Zero-Shot Generalization of Robot Manipulation Policies2025/9/1
- ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training2025/9/1
- MolmoAct: Action Reasoning Models that can Reason in Space2025/8/1
- Neural Robot Dynamics2025/8/1
- Robot Policy Evaluation for Sim-to-Real Transfer: A Benchmarking Perspective2025/8/1
- RoboEval: Where Robotic Manipulation Meets Structured and Scalable Evaluation2025/7/1
- GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training2025/7/1
- OG-VLA: Orthographic Image Generation for 3D-Aware Vision-Language Action Model2025/6/1
- RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills2025/6/1
- DreamGen: Unlocking Generalization in Robot Learning through Video World Models2025/5/1
- DexMachina: Functional Retargeting for Bimanual Dexterous Manipulation2025/5/1
- Slot-Level Robotic Placement via Visual Imitation from Single Human Video2025/4/1
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots2025/3/1
- SRSA: Skill Retrieval and Adaptation for Robotic Assembly Tasks2025/3/1
- MatchMaker: Automated Asset Generation for Robotic Assembly2025/3/1
- Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control2025/3/1
- HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation2025/2/1
- SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation2025/1/1
- Cosmos World Foundation Model Platform for Physical AI2025/1/1
- RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields2024/12/1
- Inference-Time Policy Steering through Human Interactions2024/11/1
- GRAPE: Generalizing Robot Policy via Preference Alignment2024/11/1
- Aim My Robot: Precision Local Navigation to Any Object2024/11/1
- Open-World Task and Motion Planning via Vision-Language Model Generated Constraints2024/11/1
- AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation2024/10/1
- Latent Action Pretraining from Videos2024/10/1
- SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment2024/10/1
- SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation2024/10/1
- DiffusionSeeder: Seeding Motion Optimization with Diffusion for Rapid Motion Planning2024/10/1
- Guiding Long-Horizon Task and Motion Planning with Vision Language Models2024/10/1
- Learning to Build by Building Your Own Instructions2024/10/1
- OptiGrasp: Optimized Grasp Pose Detection Using RGB Images for Warehouse Picking Robots2024/9/1
- FORGE: Force-Guided Exploration for Robust Contact-Rich Manipulation under Uncertainty2024/8/1
- TacSL: A Library for Visuotactile Sensor Simulation and Learning2024/8/1
- AutoMate: Specialist and Generalist Assembly Policies over Diverse Geometries2024/7/1
- PerAct2: Benchmarking and Learning for Robotic Bimanual Manipulation Tasks2024/7/1
- Manipulate-Anything: Automating Real-World Robots using Vision-Language Models2024/6/1
- RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics2024/6/1
- RVT-2: Learning Precise Manipulation from Few Demonstrations2024/6/1
- 3D-MVP: 3D Multiview Pretraining for Robotic Manipulation2024/6/1
- IntervenGen: Interventional Data Generation for Robust and Data-Efficient Robot Imitation Learning2024/5/1
- URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Images2024/5/1
- EVE: Enabling Anyone to Train Robots using Augmented Reality2024/4/1
- Benchmarking Population-Based Reinforcement Learning across Robotic Tasks with GPU-Accelerated Simulation2024/4/1
- ASID: Active Exploration for System Identification in Robotic Manipulation2024/4/1
- Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects2024/4/1
- AdaDemo: Data-Efficient Demonstration Expansion for Generalist Robotic Agent2024/4/1
- THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation2024/2/1
- Fast Explicit-Input Assistance for Teleoperation in Clutter2024/2/1
- M2T2: Multi-Task Masked Transformer for Object-centric Pick and Place2023/11/1
- STOW: Discrete-Frame Segmentation and Tracking of Unseen Objects for Warehouse Picking Robots2023/11/1
- cuRobo: Parallelized Collision-Free Minimum-Jerk Robot Motion Generation2023/10/1
- NEWTON: Are Large Language Models Capable of Physical Reasoning?2023/10/1
- Human-in-the-Loop Task and Motion Planning for Imitation Learning2023/10/1
- MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations2023/10/1
- AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System2023/7/1
- Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement2023/7/1
- Meta-Policy Learning over Plan Ensembles for Robust Articulated Object Manipulation2023/7/1
- DiMSam: Diffusion Models as Samplers for Task and Motion Planning under Partial Observability2023/6/1
- AR2-D2:Training a Robot Without a Robot2023/6/1
- RVT: Robotic View Transformer for 3D Object Manipulation2023/6/1
- IndustReal: Transferring Contact-Rich Assembly Tasks from Simulation to Reality2023/5/1
- Imitating Task and Motion Planning with Visuomotor Transformers2023/5/1
- CabiNet: Scaling Neural Collision Detection for Object Rearrangement with Procedural Scene Generation2023/4/1
- DefGraspNets: Grasp Planning on 3D Fields with Graph Neural Nets2023/3/1
- TerrainNet: Visual Modeling of Complex Terrain for High-speed, Off-road Navigation2023/3/1
- Learning Human-to-Robot Handovers from Point Clouds2023/3/1
- BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects2023/3/1
- Constrained Generative Sampling of 6-DoF Grasps2023/2/1
- MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare2022/12/1
- Sequence-Based Plan Feasibility Prediction for Efficient Task and Motion Planning2022/11/1
- One-Shot Neural Fields for 3D Object Understanding2022/10/1
- Motion Policy Networks2022/10/1
- DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality2022/10/1
- Learning Robust Real-World Dexterous Grasping Policies via Implicit Shape Augmentation2022/10/1
- ProgPrompt: Generating Situated Robot Task Plans using Large Language Models2022/9/1
- Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation2022/9/1
- Deep Learning Approaches to Grasp Synthesis: A Review2022/7/1
- Neural Motion Fields: Encoding Grasp Trajectories as Implicit Value Functions2022/6/1
- Factory: Fast Contact for Robotic Assembly2022/5/1
- HandoverSim: A Simulation Framework and Benchmark for Human-to-Robot Object Handovers2022/5/1
- Model Predictive Control for Fluid Human-to-Robot Handovers2022/4/1
- Correcting Robot Plans with Natural Language Feedback2022/4/1
- DefGraspSim: Physics-based simulation of grasp outcomes for 3D deformable objects2022/3/1
- DiSECt: A Differentiable Simulator for Parameter Inference and Control in Robotic Cutting2022/3/1
- IFOR: Iterative Flow Minimization for Robotic Object Rearrangement2022/2/1
- iCaps: Iterative Category-level Object Pose and Shape Estimation2022/1/1
- Assistive Tele-op: Leveraging Transformers to Collect Robotic Task Demonstrations2021/12/1
- A Bayesian Treatment of Real-to-Sim for Deformable Object Manipulation2021/12/1
- Learning Perceptual Concepts by Bootstrapping from Human Queries2021/11/1
- From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence2021/10/1
- Continuous-Time Fitted Value Iteration for Robust Policies2021/10/1
- StructFormer: Learning Spatial Structure for Language-Guided Semantic Rearrangement of Novel Objects2021/10/1
- SORNet: Spatial Object-Centric Representations for Sequential Manipulation2021/9/1
- CLIPort: What and Where Pathways for Robotic Manipulation2021/9/1
- Geometric Fabrics: Generalizing Classical Mechanics to Capture the Physics of Behavior2021/9/1
- Predicting Stable Configurations for Semantic Placement of Novel Objects2021/8/1
- BayesSimIG: Scalable Parameter Inference for Adaptive Domain Randomization with IsaacGym2021/7/1
- Hierarchical Policies for Cluttered-Scene Grasping with Latent Plans2021/7/1
- A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution2021/7/1
- LanguageRefer: Spatial-Language Model for 3D Visual Grounding2021/7/1
- DefGraspSim: Simulation-based grasping of 3D deformable objects2021/7/1
- RICE: Refining Instance Masks in Cluttered Environments with Graph Neural Networks2021/6/1
- NeRP: Neural Rearrangement Planning for Unknown Objects2021/6/1
- Value Iteration in Continuous Actions, States and Time2021/5/1
- DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cutting2021/5/1
- Robust Value Iteration for Continuous Control Tasks2021/5/1
- STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulation2021/4/1
- RGB-D Local Implicit Function for Depth Completion of Transparent Objects2021/4/1
- Sim-to-Real for Robotic Tactile Sensing via Physics-Based Simulation and Learned Latent Projections2021/3/1
- Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes2021/3/1
- Learning Composable Behavior Embeddings for Long-horizon Visual Navigation2021/2/1
- Interpreting and Predicting Tactile Signals for the SynTouch BioTac2021/1/1
- Alternative Paths Planner (APP) for Provably Fixed-time Manipulation Planning in Semi-structured Environments2020/12/1
- Perspectives on Sim2Real Transfer for Robotics: A Summary of the R:SS 2020 Workshop2020/12/1
- Towards Coordinated Robot Motions: End-to-End Learning of Motion Policies on Transform Trees2020/12/1
- STReSSD: Sim-To-Real from Sound for Stochastic Dynamics2020/11/1
- Reactive Long Horizon Task Execution via Visual Skill and Precondition Models2020/11/1
- Reactive Human-to-Robot Handovers of Arbitrary Objects2020/11/1
- Stein Variational Model Predictive Control2020/11/1
- Object Rearrangement Using Learned Implicit Collision Functions2020/11/1
- ACRONYM: A Large-Scale Grasp Dataset Based on Simulation2020/11/1
- A User's Guide to Calibrating Robotics Simulators2020/11/1
- Multimodal Trajectory Prediction via Topological Invariance for Navigation at Uncontrolled Intersections2020/11/1
- Geometric Fabrics for the Acceleration-based Design of Robotic Motion2020/10/1
- Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds2020/10/1
- Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation2020/7/1
- RMPflow: A Geometric Framework for Generation of Multi-Task Motion Policies2020/7/1
- Unseen Object Instance Segmentation for Robotic Environments2020/7/1
- Model-Based Generalization Under Parameter Uncertainty Using Path Integral Control2020/6/1
- Interpreting and Predicting Tactile Signals via a Physics-Based and Data-Driven Framework2020/6/1
- Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning2020/5/1
- Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems2020/5/1
- Transferable Task Execution from Pixels through Deep Planning Domain Learning2020/3/1
- Inferring the Material Properties of Granular Media for Robotic Tasks2020/3/1
- Human Grasp Classification for Reactive Human-to-Robot Handovers2020/3/1
- In-Hand Object Pose Tracking via Contact Feedback and GPU-Accelerated Robotic Simulation2020/2/1
- Information Theoretic Model Predictive Q-Learning2020/1/1
- A Billion Ways to Grasp: An Evaluation of Grasp Sampling Schemes on a Dense, Physics-based Grasp Data Set2019/12/1
- LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimation2019/12/1
- 6-DOF Grasping for Target-driven Object Manipulation in Clutter2019/12/1
- ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks2019/12/1
- Online Replanning in Belief Space for Partially Observable Task and Motion Problems2019/11/1
- Manipulation Trajectory Optimization with Online Grasp Synthesis and Selection2019/11/1
- Camera-to-Robot Pose Estimation from a Single Image2019/11/1
- IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data2019/11/1
- Motion Reasoning for Goal-Based Imitation Learning2019/11/1
- Contextual Reinforcement Learning of Visuo-tactile Multi-fingered Grasping Policies2019/11/1
- Riemannian Motion Policy Fusion through Learnable Lyapunov Function Reshaping2019/10/1
- Collaborative Behavior Models for Optimized Human-Robot Teamwork2019/10/1
- Motion-Nets: 6D Tracking of Unknown Objects in Unseen Environments using RGB2019/10/1
- Conditional Driving from Natural Language Instructions2019/10/1
- DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System2019/10/1
- Self-supervised 6D Object Pose Estimation for Robot Manipulation2019/9/1
- Scaling Local Control to Large-Scale Topological Navigation2019/9/1
- Part Segmentation for Highly Accurate Deformable Tracking in Occlusions via Fully Convolutional Neural Networks2019/8/1
- Representing Robot Task Plans as Robust Logical-Dynamical Systems2019/8/1
- The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentation2019/7/1
- BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators2019/6/1
- PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking2019/5/1
- 6-DOF GraspNet: Variational Grasp Generation for Object Manipulation2019/5/1
- ContactGrasp: Functional Multi-finger Grasp Synthesis from Contact2019/4/1
- Neural Autonomous Navigation with Riemannian Motion Policy2019/4/1
- Joint Inference of Kinematic and Force Trajectories with Visuo-Tactile Sensing2019/3/1
- Prospection: Interpretable Plans From Language By Predicting the Future2019/3/1
- Learning Latent Space Dynamics for Tactile Servoing2018/11/1
- RMPflow: A Computational Graph for Automatic Motion Policy Generation2018/11/1
- Early Fusion for Goal Directed Robotic Vision2018/11/1
- Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience2018/10/1
- Robust Learning of Tactile Force Estimation through Robot Interaction2018/10/1
- GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning2018/10/1
- Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects2018/9/1
- SPNets: Differentiable Fluid Dynamics for Deep Neural Networks2018/6/1
- The Limits and Potentials of Deep Learning for Robotics2018/4/1
- DeepIM: Deep Iterative Matching for 6D Pose Estimation2018/4/1
- Riemannian Motion Policies2018/1/1
- PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes2017/11/1
- SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Planning and Control2017/10/1
- Learning Robotic Manipulation of Granular Media2017/9/1
- Visual Semantic Planning using Deep Successor Representations2017/5/1
- DA-RNN: Semantic Mapping with Data Associated Recurrent Neural Networks2017/3/1
- Perceiving and Reasoning About Liquids Using Fully Convolutional Networks2017/3/1
- Reasoning About Liquids via Closed-Loop Simulation2017/3/1
- Visual Closed-Loop Control for Pouring Liquids2016/10/1
- Guided Policy Search with Delayed Sensor Measurements2016/9/1
- Towards Learning to Perceive and Reason About Liquids2016/8/1
- Detection and Tracking of Liquids with Fully Convolutional Networks2016/6/1
- SE3-Nets: Learning Rigid Body Motion using Deep Neural Networks2016/6/1
- Gaussian Processes for Data-Efficient Learning in Robotics and Control2015/2/1
- Multi-Task Policy Search2013/7/1
- The Revisiting Problem in Mobile Robot Map Building: A Hierarchical Bayesian Approach2012/12/1
- A Joint Model of Language and Perception for Grounded Attribute Learning2012/6/1