5 papers
Hybrid Feedback Sampling for Sample-Efficient Model Predictive Control
Chaoyi Pan, Zeji Yi, John Zhang +3
Thanks to its parallelizability and flexibility, sampling-based Model Predictive Control (MPC) has become widely popular for controlling real-world robotic systems. However, for hi…
PGDG: Physically Grounded Data Generation for Robust Bimanual Policy Learning from a Single Demonstration
Cunxi Dai, Haoran Chang, Aditya Nisal +5
Behavior cloning for contact-rich bimanual manipulation remains challenging because diverse demonstrations are expensive to collect, and even small disturbances can push the system…
Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing
Zeji Yi, Chaoyi Pan, Guanya Shi +1
Sampling-based optimization (SBO), like cross-entropy method and evolutionary algorithms, has achieved many successes in solving non-convex problems without gradients, yet its conv…
UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies
Harsh Gupta, Xiaofeng Guo, Huy Ha +6
We introduce UMI-on-Air, a framework for embodiment-aware deployment of embodiment-agnostic manipulation policies. Our approach leverages diverse, unconstrained human demonstration…
Much Ado About Noising: Dispelling the Myths of Generative Robotic Control
Chaoyi Pan, Giri Anantharaman, Nai-Chieh Huang +8
Generative models, like flows and diffusions, have recently emerged as popular and efficacious policy parameterizations in robotics. There has been much speculation as to the facto…