7 papers
ACE-F: A Cross Embodiment Foldable System with Force Feedback for Dexterous Teleoperation
Rui Yan, Jiajian Fu, Shiqi Yang +3
Teleoperation systems are essential for efficiently collecting diverse and high-quality robot demonstration data, especially for complex, contact-rich tasks. However, current teleo…
In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data
Xiongyi Cai, Ri-Zhao Qiu, Geng Chen +5
Egocentric videos are a valuable and scalable data source to learn manipulation policies. However, due to significant data heterogeneity, most existing approaches utilize human dat…
HMC: Learning Heterogeneous Meta-Control for Contact-Rich Loco-Manipulation
Lai Wei, Xuanbin Peng, Ri-Zhao Qiu +3
Learning from real-world robot demonstrations holds promise for interacting with complex real-world environments. However, the complexity and variability of interaction dynamics of…
Humanoid Policy ~ Human Policy
Ri-Zhao Qiu, Shiqi Yang, Xuxin Cheng +12
Training manipulation policies for humanoid robots with diverse data enhances their robustness and generalization across tasks and platforms. However, learning solely from robot de…
GMT: General Motion Tracking for Humanoid Whole-Body Control
Zixuan Chen, Mazeyu Ji, Xuxin Cheng +3
The ability to track general whole-body motions in the real world is a useful way to build general-purpose humanoid robots. However, achieving this can be challenging due to the te…
ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training
Ge Yan, Jiyue Zhu, Yuquan Deng +8
This paper introduces ManiFlow, a visuomotor imitation learning policy for general robot manipulation that generates precise, high-dimensional actions conditioned on diverse visual…