Latest

• DefGoalNet: Contextual Goal Learning from Demonstrations For Deformable Object Manipulation
• Out of Sight, Still in Mind: Reasoning and Planning about Unobserved Objects with Video Tracking Enabled Memory Models
• Point Cloud Models Improve Visual Robustness in Robotic Learners
• Latent Space Planning for Multi-Object Manipulation with Environment-Aware Relational Classifiers
• Pick and Place Planning is Better than Pick Planning then Place Planning
• Composable Part-Based Manipulation
• StructDiffusion: Language-Guided Creation of Physically-Valid Structures using Unseen Objects
• DefGraspNets: Grasp Planning on 3D Fields with Graph Neural Nets
• Planning for Multi-Object Manipulation with Graph Neural Network Relational Classifiers
• StructDiffusion: Object-Centric Diffusion for Semantic Rearrangement of Novel Objects
• Visual-Tactile Surface Estimation to Enable Multi-fingered, Precision Grasps
• DULA and DEBA: Differentiable Ergonomic Risk Models for Postural Assessment and Optimization in Ergonomically Intelligent pHRI
• Pseudo-Tractor Beam for Conductive Non-magnetic Objects using Magnetic Fields
• Correcting Robot Plans with Natural Language Feedback
• StructFormer: Learning Spatial Structure for Language-Guided Semantic Rearrangement of Novel Objects
• DefGraspSim: Physics-based simulation of grasp outcomes on 3D deformable objects
• Ergonomically Intelligent Physical Human-Robot Interaction: Postural Estimation, Assessment, and Optimization
• In Vitro Simulation of Shoulder Motion Driven by 3D Scapular and Humeral Kinematics
• Parallelised Diffeomorphic Sampling-based Motion Planning
• Planning Sensing Sequences for Subsurface 3D Tumor Mapping
• Predicting Stable Configurations for Semantic Placement of Novel Objects
• Toward Learning Context-Dependent Tasks from Demonstration for Tendon-Driven Surgical Robots
• Dexterous magnetic manipulation of conductive non-magnetic objects
• DefGraspSim: Simulation-based grasping of 3D deformable objects
• In-Hand Object-Dynamics Inference using Tactile Fingertips
• Multi-Fingered Active Grasp Learning
• Learning to Manipulate Object Collections Using Grounded State Representations
• Robust Learning of Tactile Force Estimation through Robot Interaction