12 papers · 1 filter
Active Generative Simulation: Meta-Learning What to Simulate for Sim-and-Real Policy Co-Training
Liqian Ma, Vaibhav Saxena, Utkarsh Aashu Mishra +3
Sim-and-real co-training is an effective way to scale robot learning by augmenting limited real-world demonstrations with simulation data. However, existing approaches typically tr…
Action Chunk Scheduling for Batched Robot Policy Serving
Rohan Bansal, David He, Nadun Ranawaka Arachchige +4
Deploying robot foundation models at scale is the next step towards realizing the potential of general-purpose robots. However, Vision-Language-Action (VLA) and other foundation mo…
Static In, Dynamic Out: Counterfactual Action Augmentation for Moving Object Manipulation
Woo Chul Shin, Zhenyang Chen, Alfred Cueva +5
Visuomotor policies have advanced on manipulation tasks where the target object stays static during execution, but real deployments break this assumption: parts drift on conveyors…
WARP: Whole-Body Retargeting for Learning from Offline Human Demonstrations
Zhenyang Chen, Chuizheng Kong, Chuye Zhang +4
Direct transfer from human demonstration to learnable robot action is a crucial step towards scalable whole-body mobile manipulation. While human data scales better than mobile tel…
ReSteer: Quantifying and Refining the Steerability of Multitask Robot Policies
Zhenyang Chen, Alan Tian, Liquan Wang +5
Despite strong multi-task pretraining, existing policies often exhibit poor task steerability. For example, a robot may fail to respond to a new instruction ``put the bowl in the s…
A Closed-Form Geometric Retargeting Solver for Upper Body Humanoid Robot Teleoperation
Chuizheng Kong, Yunho Cho, Wonsuhk Jung +11
Retargeting human motion to robot poses is a practical approach for teleoperating bimanual humanoid robot arms, but existing methods can be suboptimal and slow, often causing undes…
Compositional Diffusion with Guided Search for Long-Horizon Planning
Utkarsh A Mishra, David He, Yongxin Chen +1
Generative models have emerged as powerful tools for planning, with compositional approaches offering particular promise for modeling long-horizon task distributions by composing t…
Joint Model-based Model-free Diffusion for Planning with Constraints
Wonsuhk Jung, Utkarsh A. Mishra, Nadun Ranawaka Arachchige +3
Model-free diffusion planners have shown great promise for robot motion planning, but practical robotic systems often require combining them with model-based optimization modules t…
SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies
Nadun Ranawaka Arachchige, Zhenyang Chen, Wonsuhk Jung +8
Offline Imitation Learning (IL) methods such as Behavior Cloning are effective at acquiring complex robotic manipulation skills. However, existing IL-trained policies are confined…
Generative Trajectory Stitching through Diffusion Composition
Yunhao Luo, Utkarsh A. Mishra, Yilun Du +1
Effective trajectory stitching for long-horizon planning is a significant challenge in robotic decision-making. While diffusion models have shown promise in planning, they are limi…
RAIL: Reachability-Aided Imitation Learning for Safe Policy Execution
Wonsuhk Jung, Dennis Anthony, Utkarsh A. Mishra +4
Imitation learning (IL) has shown great success in learning complex robot manipulation tasks. However, there remains a need for practical safety methods to justify widespread deplo…
Generative Factor Chaining: Coordinated Manipulation with Diffusion-based Factor Graph
Utkarsh A. Mishra, Yongxin Chen, Danfei Xu
Learning to plan for multi-step, multi-manipulator tasks is notoriously difficult because of the large search space and the complex constraint satisfaction problems. We present Gen…