arXiv · 2611.22797
Zero-Shot Compositional Generalization for Embodied Manipulation
Abstract
Robot demonstrations are collected on different embodiments, leaving many robot-skill combinations unobserved. Pooling these data shares visual knowledge, while joint labels remain tied to the demonstrating kinematic chain. We propose a geometry-supervised training framework for zero-shot composition of familiar robots and skills. The central insight is that a demonstrated command provides a tool-space target for every robot that can realize it. Calibrated forward kinematics supplies this supervision to foreign native action interfaces without their joint labels for that skill. Native reconstruction retains demonstrated configurations, and positive reachability checks select targets for cross-robot supervision. A visual policy learns to predict shared actions and executes through the target robot's native decoder. During policy learning, one prediction receives geometric supervision through both source and foreign native realizations. Matched supervision controls, repeated policy training and evaluations across three backbones and two simulators demonstrate improved transfer to missing robot-task combinations.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Baicheng Li, Wenkang Qin, Youqi Pan, Dongxiao Mao, Yukun Zhou, Chuanfu Shen, Dong Wu, Shunkai Zhou, Zike Yan, Wei Sui, Hongbin Zha. 2026-11-17. Zero-Shot Compositional Generalization for Embodied Manipulation. https://searcharxiv.com/abs/2611.22797
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.