ORPA: 人間のフィードバックを用いたロボット操作制御のためのオンライン残差ポリシー適応
ORPA: Online Residual Policy Adaptation for Robot Manipulation Control with Human Feedback
模倣学習で訓練された操作ポリシーの実行時エラーを、基盤ポリシーを変更せずに軽量なフィードバック条件付きモジュールで残差補正するフレームワークを提案し、ALOHAプラットフォームでの精密操作タスクで成功率向上を実証した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Muhammad A. Muttaqien, Tomohiro Motoda, Ryo Hanai, Yukiyasu Domae
分類: cs.RO, cs.AI
原文アブストラクト
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. In this work, we propose Online Residual Policy Adaptation (ORPA), a framework that enables immediate, feedback-driven correction of robot actions without modifying the underlying policy parameters. ORPA augments a pretrained control policy with a lightweight, feedback-conditioned module that predicts residual adjustments directly in joint space, allowing the system to adapt its behavior at runtime. We evaluate ORPA on a set of precision-sensitive manipulation tasks using the ALOHA platform, demonstrating improvements in success rate and recovery from small perturbations compared to baseline control policies and rule-based inverse kinematics corrections.