言語フィードバックによるVLAモデル失敗の訓練不要な行動補正
Training-Free Action Correction for VLA Model Failures via Language Feedback
VLAモデルの実行時失敗を、再訓練なしにタスクレベルの自然言語補正で行動の大きさを調整して修正するフレームワークCorrectVLAを提案。シミュレーションと実ロボットで有効性を示し、修正可能な失敗の境界を明らかにした。
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: Owen Kwon, Pablo Ortega-Kral, Arthur Bucker, Jean Oh
分類: cs.RO, cs.AI
原文アブストラクト
Vision-Language-Action (VLA) models demonstrate strong semantic understanding yet exhibit systematic failures during deployment. The conditions under which these failures occur, and whether they can be corrected without retraining, remain poorly understood. In this paper, we take steps toward addressing this gap. We present CorrectVLA, a framework that translates task-level natural language corrections into additive action magnitude adjustments without modifying policy weights. A human provides a single task-level correction, applied uniformly across all rollouts without per-episode intervention. In simulation, CorrectVLA recovers execution misalignment failures across both in-distribution and OOD tasks. In real-robot experiments on a UFactory xArm7 under environment shift, CorrectVLA restores near-perfect success where the base policy almost entirely breaks down, generalizing across object locations and identities. Through a taxonomy of failure modes on LIBERO-90, we find that execution misalignment failures, where the policy reaches the correct target but miscalibrates action magnitudes, represent the correctable subset, while other failure modes where semantic comprehension itself breaks down are not amenable to this approach. The approach succeeds when policies possess strategic correctness and fails when fundamental comprehension is absent, establishing a practical operational boundary for inference-time correction.