20 papers
ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Learning
Zihan Zhou, Animesh Garg, Ajay Mandlekar +1
Long-horizon manipulation has been a long-standing challenge in the robotics community. We propose ReinforceGen, a system that combines task decomposition, data generation, imitati…
SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation
Nadun Ranawaka, Josiah Wong, Wei-Lin Pai +15
Training and evaluating robot policies in the real world is costly and difficult to scale. We introduce SimFoundry, a modular and automated system for zero-shot real-to-sim scene c…
ASPIRE: Agentic /Skills Discovery for Robotics
Runyu Lu, Yubo Wu, Ethan Kou +11
Traditional robot programming is challenging: it requires orchestrating multimodal perception, managing physical contact dynamics, and handling diverse configurations and execution…
Human2Any: Human-to-Robot Transfer via Constraint-Aware Compositional Planning
Shuo Cheng, Chuye Zhang, Alfred Cueva +3
Human videos are a scalable source of supervision for robot manipulation, as they are abundant and naturally capture rich object interactions. However, transferring human demonstra…
GRAFT: Graph-Based Affordance Transfer via Part Correspondence
Mengying Lin, Utkarsh Mishra, Ajay Mandlekar +1
Generalizing robotic manipulation to unseen objects remains challenging, as learning-based approaches require many demonstrations and fail in few-shot settings. Prior work transfer…
HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning
Kevin Lin, Ajay Mandlekar, Caelan Reed Garrett +7
Imitation learning is a promising approach for training humanoid robots to both walk and manipulate, but it requires a large number of demonstrations, which are time-intensive and…