Fail2Progress: 実世界のロボット失敗からシュタイン変分推論で学ぶ
Fail2Progress: Learning from Real-World Robot Failures with Stein Variational Inference
ロボットの失敗に似たシミュレーション環境をシュタイン変分推論で並列生成し、スキル効果モデルを微調整することで失敗からの回復と再発防止を実現する手法を提案。
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: Yixuan Huang, Novella Alvina, Mohanraj Devendran Shanthi, Tucker Hermans
分類: cs.RO
原文アブストラクト
Skill effect models for long-horizon manipulation tasks are prone to failures in conditions not covered by training data distributions. Therefore, enabling robots to reason about and learn from failures is necessary. We investigate the problem of efficiently generating a dataset targeted to observed failures. After fine-tuning a skill effect model on this dataset, we evaluate the extent to which the model can recover from failures and minimize future failures. We propose Fail2Progress, an approach that leverages Stein variational inference to generate multiple simulation environments in parallel, enabling efficient data sample generation similar to observed failures. Our method is capable of handling several challenging mobile manipulation tasks, including transporting multiple objects, organizing a constrained shelf, and tabletop organization. Through large-scale simulation and real-world experiments, we demonstrate that our approach excels at learning from failures across different numbers of objects. Furthermore, we show that Fail2Progress outperforms several baselines.
