Embodied Intelligence Observer

ORPA: Online Residual Policy Adaptation for Robot Manipulation Control with Human Feedback

Research

Source: arXiv cs.ROPublish time unverified

arXiv:2608.17323v2 Announce Type: replace Abstract: Robotic manipulation policies trained via imitation learning, such as Action Chunking with Transformers (ACT), can achieve strong performance under ideal conditions but often remain sensitive to small execution errors and distribution shifts. Correcting these failures typically requires dataset aggregation and full-policy retraining, which is computationally expensive and unsuitable for real-time deployment.

ORPA: Online Residual Policy Adaptation for Robot Manipulation Control with Human Feedback | Embodied Intelligence Observer