必要なときだけ行動を洗練：ロボットマニピュレーションのための適応的行動チャンク洗練
Refine Actions If Needed: Adaptive Action Chunk Refinement for Robot Manipulation
軽量ポリシーの行動提案に対し、洗練が必要か・どれだけ必要かを事前に予測して動的に洗練を行うRAINを提案し、シミュレーションと実機で成功率向上と低遅延を両立した。
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: Hanlin Liu, Zichen Zhou, Jiacheng Zhang, Liuyuan Na, Jin Jin, Guangyan Chen, Yufeng Yue, Gen Li, Fangqiang Ding
分類: cs.RO
原文アブストラクト
Computationally lightweight manipulation policies predict executable actions with low inference latency, but prediction errors can limit task success. Iterative generative policies can achieve higher task success rates, but repeated network evaluations increase inference latency. Refining action proposals from computationally lightweight policies can combine these strengths, but the amount of refinement needed varies across states. We introduce RAIN (Refine Actions If Needed), a framework that predicts action errors at different refinement levels to decide whether and how much to refine each executable proposal, before performing any refinement. We train an ensemble to predict these errors by comparing action proposals and their refined versions with expert actions from offline demonstrations, without requiring explicit labels of refinement needs. Calibration balances uncertainty, computation, and temporal consistency. We evaluate RAIN on eight ManiSkill tasks and four real-robot tasks. In simulation, our policy achieves 66.6% success, approaching the best evaluated diffusion-policy success rate with 5.71 times lower policy latency. On the real robot, success increases from 55.0% with Action Chunking with Transformers (ACT) to 72.5%, with comparable average successful completion time. Matched controls show that dynamic routing maintains the strongest observed fixed-refinement success level with 26.6% fewer refiner evaluations. Project page: https://rain-policy.github.io/.