4 papers
TRACT: Temporally Routed Action Chunks with Chronological Phase Authority for Contact-Rich Manipulation
Jiahao Liu, Kento Kawaharazuka, Tasuku Makabe +1
Action chunking shortens the effective decision horizon of robot imitation learning by predicting multiple future actions, while conventional phase conditioning describes the curre…
MDIR: A Task-Manifold Impedance Retargeting Method for Contact-Rich Teleoperation
Liu Jiahao, Kento Kawaharazuka, Tasuku Makabe +1
Fixed Cartesian impedance makes contact-rich teleoperation demonstrations practical, but gains that secure progress and contact support also determine impact and force variability.…
WALA Learning Executable Latent Actions from Action-Labeled Demonstrations and Action-Free Videos
Jiahao Liu, Zhongpu Xia, Shuai Tian +13
Generalizable robot policies typically rely on action-labeled robot demonstrations, which are expensive to collect and difficult to scale. In contrast, large-scale human and robot…
InCoM: Intent-Driven Perception and Structured Coordination for Mobile Manipulation
Jiahao Liu, Cui Wenbo, Zhongpu Xia +3
Mobile manipulation is a fundamental capability for general-purpose robotic agents, requiring both coordinated control of the mobile base and manipulator and robust perception unde…