Abstract:Large behaviour models have transformed the field of robotic manipulation, but prohibitive data requirements have thus far prevented a revolution similar to vision language models. We believe that instrumentation, i.e. sensor integration in objects, can provide invaluable state information and enable efficient learning for robotic manipulation. In this paper, we present instrumented imitation learning of clothes hanger insertion. Using 180 teleoperated demonstrations, we train diffusion policies with and without access to instrumentation data. Results show that policies leveraging instrumentation outperform vision-only counterparts by 14-25 %pt and exhibit greater task awareness. Crucially, a black-box imitation learning policy learns to prioritise instrumentation signals without explicit guidance. In addition, enhancing the teleoperation dataset with rollouts from an instrumented expert policy, enables a vision-only student policy to achieve performance comparable to the instrumented expert, thereby surpassing the original vision-only policy. These findings establish instrumentation as a promising strategy to enhance imitation learning for robotic manipulation. Datasets are available on Zenodo.
| Comments: | Accepted for presentation at ICRA2026 |
| Subjects: | Robotics (cs.RO) |
| Cite as: | arXiv:2605.23847 [cs.RO] |
| (or arXiv:2605.23847v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2605.23847 arXiv-issued DOI via DataCite (pending registration) |
From: Remko Proesmans [view email]
[v1]
Fri, 22 May 2026 16:59:55 UTC (4,277 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。