6 papers
KeyGen: Unsupervised Keypoint based Object-Centric Representations for Category-Level Policy Generalization
Shuxin Cao, Liquan Wang, Masoud Moghani +2
Generalization in robotic manipulation requires policies to perform tasks across diverse unseen object instances that vary in shape, size, and pose. However, conventional behavior…
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…
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…
AMPLIFY: Actionless Motion Priors for Robot Learning from Videos
Jeremy A. Collins, Loránd Cheng, Kunal Aneja +3
Action-labeled data for robotics is scarce and expensive, limiting the generalization of learned policies. In contrast, vast amounts of action-free video data are readily available…
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…
Adapt3R: Adaptive 3D Scene Representation for Domain Transfer in Imitation Learning
Albert Wilcox, Mohamed Ghanem, Masoud Moghani +3
Imitation Learning can train robots to perform complex and diverse manipulation tasks, but learned policies are brittle with observations outside of the training distribution. 3D s…