CARE: 経験に基づく原子的修正実行によるVision-Language-Actionポリシーの回復
CARE: Experience-Guided Atomic Corrective Execution for Vision-Language-Action Policies
VLAポリシーの失敗ロールアウトから段階別の失敗分布を学習し、推論時に3Dモニタリングで原子的な修正動作をトリガーすることで、ロボット操作の回復性能を向上させるフレームワーク。
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: Junlan Xiao, Junwei Jiang, Zaibin Zhang, Yifan Wang, Zhongbo Zhang, Huchuan Lu, Lijun Wang
分類: cs.RO
原文アブストラクト
Vision-Language-Action (VLA) policies achieve strong performance in robotic manipulation but remain brittle once execution deviates from nominal trajectories. We propose CARE (Corrective Atomic Robotic Execution), a framework that improves recovery by learning from failures encountered during execution. Instead of generating corrective data from manually designed or random perturbations, CARE collects failed rollouts, models stage-conditioned post-failure deviations, and uses the resulting empirical distributions to synthesize representative failure states and corrective demonstrations. At inference time, CARE combines stage-wise planning with physically grounded 3D monitoring to trigger atomic adjustments or re-operations while preserving task progress. We further introduce the Failure State Recovery Benchmark (FSR-Bench), which evaluates recovery from intermediate failure states under local deviations and structural anomalies. Experiments across multiple VLA backbones, simulation benchmarks, and real-world dual-arm tasks show consistent improvements, with average task-success gains of 14.5 points in simulation and 15.9 points in the real world. Code, models, and data are available at https://github.com/xiaojunlan/care