Co-Evolving Robot Orchestrators and Policies through Deployment
Co-Evolving Robot Orchestrators and Policies through Deployment
This research proposes Robo-COP, a system where robot policies and orchestrators evolve together during deployment. By curating skill demonstrations and fine-tuning policies based on real-world performance, Robo-COP improves task success rates in both simulated and real-world tasks, demonstrating a self-improving deployment process.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- code: Available Artifact link Open source S5
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
-tuning on a fixed schedule without verification reaches only 65.8%. On three real-world tasks, Robo-COP raises held-out success from 38.3% to 50.0%. Robo-COP turns deployment into a self-improving flywheel in which robots learn by doing, with each improvement in execution producing better data for the next round of learning. Videos and code are available at https://robo-cop.pages.dev/.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org