SAIL: VLMを用いた文脈内模倣学習のためのテスト時スケーリング
SAIL: Test-Time Scaling for In-Context Imitation Learning with VLM
ロボットの模倣学習を反復的な軌道改善問題として捉え、モンテカルロ木探索と視覚言語モデルによる評価でテスト時の計算量を増やすほど成功率を高めるフレームワークSAILを提案。
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: Makoto Sato, Yusuke Iwasawa, Yujin Tang, So Kuroki
分類: cs.RO, cs.AI
原文アブストラクト
In-context imitation learning allows robots to acquire skills from demonstrations, yet one-shot trajectory generation remains fragile under environmental variation. We propose SAIL, a framework that reframes robot imitation as an iterative refinement problem capable of scaling with test-time compute. SAIL utilizes Monte Carlo Tree Search, where each node is a complete trajectory and edges correspond to trajectory refinements. The process is guided by three core components: an automated archive of successful trajectories for contextually relevant retrieval, a vision language model-based scoring mechanism for trajectory evaluation, and a step-level feedback that provides trajectory-aligned scores for iterative refinement. Experiments across six diverse manipulation tasks in simulation and real-world validation clearly demonstrate that increasing test-time compute consistently improves success rates, achieving up to 95% on complex tasks. Our results suggest that trajectory-level test-time scaling is a robust path toward more generalizable robotic agents.
