Cross-Behavior Learning With Object Flow Prediction for Robotic Manipulation
IEEE Transactions on Robotics · 2026 · 42 · 2631-2647
DOI: 10.1109/tro.2026.3701576 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Robotics, 2026. Verfasst von Longrui Chen und 3 weiteren Autor:innen. Die Arbeit nennt 71 Literaturangaben. Gefördert von: U.K. Engineering and Physical Sciences Research Council.
Abstract (Originalsprache)
Cross-embodiment learning enables robots to acquire manipulation skills by learning from demonstrations provided by different embodiments. However, most existing research on cross-embodiment learning focuses on transferring similar manipulation behaviors. For the same task, different embodiments may need different behaviors, e.g., it may be easier for a human to push an object to a goal position, while a robot may use a pick-and-place to perform the same task. Making use of such cross-embodiment and cross-behavior demonstrations becomes essential for large-scale imitation learning. In this work, we propose a novel framework for cross-behavior learning based on object flow. Object flow represents the task in a manner that is independent from the embodiment and the particular behavior used during the demonstration. By shifting the focus from the manipulator to objects, our framework enables learning from cross-behavior manipulation data rather than merely imitating the behavior of a specific embodiment. Our results on task representations show that, with only 20 robot demonstrations, integrating object flow prediction improves success rates by up to 91% in-domain and 87% out-of-domain. Adding 40 human demonstrations in addition to the 20 robot demonstrations further boosts out-of-domain performance by 143%.
Förderung
- U.K. Engineering and Physical Sciences Research Council
Zitieren
APA
Chen, L., Russell, D., Qiu, Y., & Dogar, M. (2026). Cross-Behavior Learning With Object Flow Prediction for Robotic Manipulation. IEEE Transactions on Robotics, 42, 2631-2647. https://doi.org/10.1109/tro.2026.3701576
Vancouver
Chen L, Russell D, Qiu Y, Dogar M. Cross-Behavior Learning With Object Flow Prediction for Robotic Manipulation. IEEE Transactions on Robotics. 2026;42:2631-2647. doi:10.1109/tro.2026.3701576
BibTeX
@article{Chen2026,
author = {Chen, Longrui and Russell, David and Qiu, Yulei and Dogar, Mehmet},
title = {Cross-Behavior Learning With Object Flow Prediction for Robotic Manipulation},
journal = {IEEE Transactions on Robotics},
year = {2026},
volume = {42},
pages = {2631--2647},
doi = {10.1109/tro.2026.3701576}
}
EUVIMED