5 papers
Accelerating Residual Reinforcement Learning with Uncertainty Estimation
Lakshita Dodeja, Karl Schmeckpeper, Shivam Vats +4
Residual Reinforcement Learning (RL) is a popular approach for adapting pretrained policies by learning a lightweight residual policy that provides corrective actions. While Residu…
Self-Improving Loops for Visual Robotic Planning
Calvin Luo, Zilai Zeng, Mingxi Jia +2
Video generative models trained on expert demonstrations have been utilized as performant text-conditioned visual planners for solving robotic tasks. However, generalization to uns…
V-HOP: Visuo-Haptic 6D Object Pose Tracking
Hongyu Li, Mingxi Jia, Tuluhan Akbulut +3
Humans naturally integrate vision and haptics for robust object perception during manipulation. The loss of either modality significantly degrades performance. Inspired by this mul…
Learning Efficient and Robust Language-conditioned Manipulation using Textual-Visual Relevancy and Equivariant Language Mapping
Mingxi Jia, Haojie Huang, Zhewen Zhang +7
Controlling robots through natural language is pivotal for enhancing human-robot collaboration and synthesizing complex robot behaviors. Recent works that are trained on large robo…
Optimal Interactive Learning on the Job via Facility Location Planning
Shivam Vats, Michelle Zhao, Patrick Callaghan +4
Collaborative robots must continually adapt to novel tasks and user preferences without overburdening the user. While prior interactive robot learning methods aim to reduce human e…