cs.RONov 17, 2026

Zero-Shot Compositional Generalization for Embodied Manipulation

Authors: Baicheng Li, Wenkang Qin, Youqi Pan, Dongxiao Mao, Yukun Zhou, Chuanfu Shen, Dong Wu, Shunkai Zhou, 

Organizations: Peking University · D-Robotics · Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China · Hong Kong Embodied AI Lab, The Chinese University of Hong Kong (CUHK)

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.

Figures & tables

Explore similar work

CardsList
  1. Decompose and Recompose: Reasoning New Skills from Existing Abilities for Cross-Task Robotic Manipulation

    May 2, 2026Xitie Zhang, Aming Wu, Yahong HanICL for RoboticsZero-Shot Robotic Manipulation

  2. UniLatent: Cross-Embodiment Transfer via Latent Observation Alignment

    Nov 6, 2026Yufei Ding, Yi Du, Weiduo Yuan +5Cross-Embodiment TransferLatent Space Alignment

  3. One-Shot Cross-Geometry Skill Transfer through Part Decomposition

    Apr 16, 2026Skye Thompson, Ondrej Biza, George KonidarisRobot Skill LearningGeneralization in Robotic Manipulation