細部にこだわるロボット批評家
Robot Critics that Sweat the Small Stuff
ロボット操作の成功と失敗を細かく見分ける批評家を、成功・失敗ロールアウトからペアの進捗監視で微調整し、候補行動の選択精度を向上させた。
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: Sruthi Sudhakar, Junbang Liang, Sreehari Rammohan, Pavel Tokmakov, Richard Zemel, Carl Vondrick
分類: cs.RO
原文アブストラクト
Large vision-language models contain several priors about the world and object interactions, making them useful critics during inference to steer robot policies towards success. However, closed-loop robot manipulation requires judging small visual differences between success and failure, which remains a challenge for current VLMs. We introduce a method to fine-tune critics by constructing pairwise progress supervision using success and failure rollouts obtained from a policy. Our fine-tuned critic excels at fine-grained progress reasoning and subtle failure detection, outperforming prior progress reasoning baselines. Additionally, we use an action-conditioned video model to predict the visual effect of several candidate actions sampled from a policy, and show that our critic can correctly identify successful candidates to execute, improving the average policy success rate by 11% across real-world tasks and 5.9% across simulation tasks.
