Latest

• Avoid Everything: Model-Free Collision Avoidance with Expert-Guided Fine-Tuning
• DiffusionSeeder: Seeding Motion Optimization with Diffusion for Rapid Motion Planning
• Manipulate-Anything: Automating Real-World Robots using Vision-Language Models
• RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics
• SkillGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment
• SPIRE: Synergistic Planning, Imitation, and Reinforcement for Long-Horizon Manipulation
• DiMSam: Diffusion Models as Samplers for Task and Motion Planning under Partial Observability
• Fast Explicit-Input Assistance for Teleoperation in Clutter
• Interventional Data Generation for Robust and Data-Efficient Robot Imitation Learning
• AutoMate: Specialist and Generalist Assembly Policies over Diverse Geometries
• RVT-2: Learning Precise Manipulation from Few Demonstrations
• THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation
• URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Images
• Human-In-The-Loop Task and Motion Planning for Imitation Learning
• Imitating Task and Motion Planning with Visuomotor Transformers
• M2T2: Multi-task Masked Transformer for Object-centric Pick-and-Place
• MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations
• RVT: Robotic View Transformer for 3D Object Manipulation
• STOW: Discrete-Frame Segmentation and Tracking of Unseen Objects for Warehouse Picking Robots
• AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System
• IndustReal: Transferring Contact-Rich Assembly from Simulation to Reality
• Sequence-Based Plan Feasibility Prediction for Efficient Task and Motion Planning
• CabiNet: Scaling Neural Collision Detection for Object Rearrangement with Procedural Scene Generation
• CuRobo: Parellelized Collision-Free Robot Motion Generation
• DefGraspNets: Grasp Planning on 3D Fields with Graph Neural Nets
• DeXtreme: Transferring Agile In-hand Manipulation from Simulation to Reality
• Learning Human-to-Robot Handovers from Point Clouds
• Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects
• ProgPrompt: Generating Situated Robot Task Plans using Large Language Models
• Bayesian Object Models for Robotic Interaction with Differentiable Probabilistic Programming
• Insights towards Sim2Real Contact-Rich Manipulation
• Learning Robust Real-World Dexterous Grasping Policies via Implicit Shape Augmentation
• MegaPose: 6D Pose Estimationof Novel Objects via Render & Compare
• Motion Policy Networks
• Neural Geometric Fabrics: Efficiently Learning High-Dimensional Policies from Demonstration
• Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation
• Sequence-Based Plan Feasibility Prediction for Efficient Task and Motion Planning
• Learning Perceptual Concepts by Bootstrapping from Human Queries
• DiSECt: A Differentiable Simulator for Parameter Inference and Control in Robotic Cutting
• Correcting Robot Plans with Natural Language Feedback
• Factory: Fast Contact for Robotic Assembly
• IFOR: Iterative Flow Minimization for Robotic Object Rearrangement
• Geometric Fabrics: Generalizing Classical Mechanics to Capture the Physics of Behavior
• HandoverSim: A Simulation Framework and Benchmark for Human-to-Robot Object Handovers
• Model Predictive Control for Fluid Human-to-Robot Handovers
• A Bayesian Treatment of Real-to-Sim for Deformable Object Manipulation
• DefGraspSim: Physics-based simulation of grasp outcomes on 3D deformable objects
• Assistive Tele-op: Leveraging Transformers to Collect Robotic Task Demonstrations
• A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution
• CLIPort: What and Where Pathways for Robotic Manipulation
• Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds
• Predicting Stable Configurations for Semantic Placement of Novel Objects
• RICE: Refining Instance Masks in Cluttered Environments with Graph Neural Networks
• SORNet: Spatial Object-Centric Representations for Sequential Manipulation
• STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulation
• Towards Coordinated Robot Motions: End-to-End Learning of Motion Policies on Transform Trees
• A differentiable simulator for robotic cutting
• DefGraspSim: Simulation-based grasping of 3D deformable objects
• DiSeCT: A differentiable simulation engine for autonomous robotic cutting
• NeRP: Neural Rearrangement Planning for Unknown Objects
• Robust Value Iteration for Continuous Control Tasks.
• Value Iteration in Continuous Actions, States and Time.
• ACRONYM: A Large-Scale Grasp Dataset Based on Simulation
• Alternative Paths Planner (APP) for Provably Fixed-time Manipulation Planning in Semi-structured Environments
• Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes
• DexYCB: A Benchmark for Capturing Hand Grasping of Objects
• Object Rearrangement Using Learned Implicit Collision Functions
• Reactive Human-to-Robot Handovers of Arbitrary Objects
• RGB-D Local Implicit Function for Depth Completion of Transparent Objects
• Sim-to-Real for Robotic Tactile Sensing via Physics-Based Simulation and Learned Latent Projections
• Learning Composable Behavior Embeddings for Long-horizon Visual Navigation
• Interpreting and Predicting Tactile Signals for the SynTouch BioTac
• Causal Discovery in Physical Systems from Videos.
• A User's Guide to Calibrating Robotics Simulators
• Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation
• RMPflow: A Geometric Framework for Generation of Multi-Task Motion Policies
• Stein Variational Model Predictive Control
• STReSSD: Sim-to-Real from Sound for Stochastic Dynamics
• Towards Coordinated Robot Motions: End-to-End Learning of Motion Policies on Transform Trees
• Collaborative Interaction Models for Optimized Human-Robot Teamwork
• Human Grasp Classification for Reactive Human-to-Robot Handovers
• Online BayesSim for Combined Simulator Parameter Inference and Policy Improvement
• Interpreting and Predicting Tactile Signals via a Physics-Based and Data-Driven Framework
• Manipulation Trajectory Optimization with Online Grasp Synthesis and Selection
• “Zero-shot” Task Execution through Learning of Pixel-Based Action Preconditions
• 6-DOF Grasping for Target-driven Object Manipulation in Clutter
• Camera-to-Robot Pose Estimation from a Single Image
• DexPilot: Depth-Based Teleoperation of Dexterous Robotic Hand-Arm System
• Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems
• Guided Uncertainty-Aware Policy Optimization: Combining Model-Free and Model-Based Strategies for Sample-Efficient Learning
• Implicit Reinforcement without Interaction at Scale: Leveraging Large-Scale Robot Manipulation Datasets for Control
• In-Hand Object Pose Tracking via Contact Feedback and GPU-Accelerated Robotic Simulation
• Inferring the Material Properties of Granular Media for Robotic Tasks
• Information Theoretic Model Predictive Q-Learning
• LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimation
• Model-based Generalization under Parameter Uncertainty using Path Integral Control
• Motion Reasoning for Goal-Based Imitation Learning
• Online Replanning in Belief Space for Partially Observable Task and Motion Problems
• Scaling Local Control to Large-Scale Topological Navigation
• Self-supervised 6D Object Pose Estimation for Robot Manipulation
• Combining Model-Free and Model-Based Strategies for Sample-Efficient Reinforcement Learning
• RMPflow: A Computational Graph for Automatic Motion Policy Generation
• ContactGrasp: Functional Multi-finger Grasp Synthesis from Contact
• Early Fusion for Goal Directed Robotic Vision
• Representing Robot Task Plans as Robust Logical-Dynamical Systems
• 6-DOF GraspNet: Variational Grasp Generation for Object Manipulation
• A Billion Ways to Grasp: An Evaluation of Grasp Sampling Schemes on a Dense, Physics-based Grasp Data Set
• Conditional Driving from Natural Language Instructions
• Learning Reactive Motion Policies in Multiple Task Spaces from Human Demonstrations
• The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentation
• BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators
• PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking
• Robust Learning of Tactile Force Estimation through Robot Interaction
• Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects
• PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
• Riemannian Motion Policies