PPGuide: 性能予測ガイダンスによる拡散ポリシーの操縦
PPGuide: Steering Diffusion Policies with Performance Predictive Guidance
拡散ポリシーの推論時に、自己教師あり学習で訓練した性能予測器の勾配を用いて失敗を回避する軽量なガイダンス手法を提案し、RobomimicとMimicGenベンチマークで性能向上を確認した。
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: Zixing Wang, Devesh K. Jha, Ahmed H. Qureshi, Diego Romeres
分類: cs.RO
原文アブストラクト
Diffusion policies have shown to be very efficient at learning complex, multi-modal behaviors for robotic manipulation. However, errors in generated action sequences can compound over time which can potentially lead to failure. Some approaches mitigate this by augmenting datasets with expert demonstrations or learning predictive world models which might be computationally expensive. We introduce Performance Predictive Guidance (PPGuide), a lightweight, classifier-based framework that steers a pre-trained diffusion policy away from failure modes at inference time. PPGuide makes use of a novel self-supervised process: it uses attention-based multiple instance learning to automatically estimate which observation-action chunks from the policy's rollouts are relevant to success or failure. We then train a performance predictor on this self-labeled data. During inference, this predictor provides a real-time gradient to guide the policy toward more robust actions. We validated our proposed PPGuide across a diverse set of tasks from the Robomimic and MimicGen benchmarks, demonstrating consistent improvements in performance.
関連論文
- 動的補正を備えた閉ループアクションチャンクによる学習不要の拡散ポリシー拡散ポリシー/操作
