自己修正VLA:スパースな世界想像によるオンライン行動洗練
Self-Correcting VLA: Online Action Refinement via Sparse World Imagination
VLAモデルに将来予測ヘッドを追加し、予測したスパースな未来状態に基づいて報酬を再形成することで、オンラインで行動を自己修正する手法を提案。シミュレーションと実機で成功率と効率が向上。
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: Chenyv Liu, Wentao Tan, Lei Zhu, Fengling Li, Jingjing Li, Guoli Yang, Heng Tao Shen
分類: cs.RO, cs.AI, cs.CV
原文アブストラクト
Standard vision-language-action (VLA) models rely on fitting statistical data priors, limiting their robust understanding of underlying physical dynamics. Reinforcement learning enhances physical grounding through exploration yet typically relies on external reward signals that remain isolated from the agent's internal states. World action models have emerged as a promising paradigm that integrates imagination and control to enable predictive planning. However, they rely on implicit context modeling, lacking explicit mechanisms for self-improvement. To solve these problems, we propose Self-Correcting VLA (SC-VLA), which achieve self-improvement by intrinsically guiding action refinement through sparse imagination. We first design sparse world imagination by integrating auxiliary predictive heads to forecast current task progress and future trajectory trends, thereby constraining the policy to encode short-term physical evolution. Then we introduce the online action refinement module to reshape progress-dependent dense rewards, adjusting trajectory orientation based on the predicted sparse future states. Evaluations on challenging robot manipulation tasks from simulation benchmarks and real-world settings demonstrate that SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher success rate than the best-performing baselines, alongside a 14% gain in real-world experiments. Code is available at https://github.com/Kisaragi0/SC-VLA.
