Latest

• NOD-TAMP: Generalizable Long-Horizon Planning with Neural Object Descriptors
• SkillGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment
• Interventional Data Generation for Robust and Data-Efficient Robot Imitation Learning
• Signatures Meet Dynamic Programming: Generalizing Bellman Equations for Trajectory Following
• Human-In-The-Loop Task and Motion Planning for Imitation Learning
• Imitating Task and Motion Planning with Visuomotor Transformers
• MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations
• Active Task Randomization: Learning Visuomotor Skills for Sequential Manipulation by Proposing Feasible and Novel Tasks
• ORBIT : A Unified Simulation Framework for Interactive Robot Learning Environments
• Learning and Retrieval from Prior Data for Skill-based Imitation Learning
• MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
• MoCoDA: Model-based Counterfactual Data Augmentation
• S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning in Robotics
• Scaling Robot Supervision to Hundreds of Hours with RoboTurk: Robotic Manipulation Dataset through Human Reasoning and Dexterity
• AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers