3 papers
cs.RO2025
Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories
Sunshine Jiang, Xiaolin Fang, Nicholas Roy +3
Recent advances in diffusionflow-matching policies have enabled imitation learning of complex, multi-modal action trajectories. However, they are computationally expensive becau…
cs.RO2025
FORGE: Force-Guided Exploration for Robust Contact-Rich Manipulation under Uncertainty
Michael Noseworthy, Bingjie Tang, Bowen Wen +7
We present FORGE, a method for sim-to-real transfer of force-aware manipulation policies in the presence of significant pose uncertainty. During simulation-based policy learning, F…
cs.RO2024
Semi-Supervised Neural Processes for Articulated Object Interactions
Emily Liu, Michael Noseworthy, Nicholas Roy
The scarcity of labeled action data poses a considerable challenge for developing machine learning algorithms for robotic object manipulation. It is expensive and often infeasible…