TwinBridge:デジタルツインによる方策と報酬の転移で実世界強化学習を実現する実験室ロボティクス
TwinBridge: Digital Twin-Driven Policy and Reward Transfer for Real-World Reinforcement Learning in Laboratory Robotics
3Dガウシアンスプラッティングと物理シミュレーションでデジタルツインを構築し、シミュレータ由来の方策初期化と視覚報酬モデルを実世界のオンライン強化学習に転移することで、実験室の5タスクを高成功率かつ短時間で学習できるようにした。
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: Shu'ang Sun, Yibo Qiu, Haoliang Ye, Zan Huang, Ao Tian, Kan Ding, Ronald Xu, Mingzhai Sun
分類: cs.RO
原文アブストラクト
Online reinforcement learning offers an effective approach to precise laboratory manipulation, yet costly real-world demonstrations and limited access to dense process rewards hinder its practical application. We present TwinBridge, a digital twin-driven framework that supplies policy initialization and dense visual rewards for real-world online learning. We construct digital twins by combining 3D Gaussian splatting with physics simulation. Here, simulator states provide task events and geometric progress under physical prerequisites and ordering constraints, yielding rewards for policy pretraining with simulated demonstrations and reinforcement learning. We distill this supervision into a visual reward model. During real-world interaction, its predictions are combined with execution history to compute dense rewards for human-in-the-loop policy refinement. Across five real-world laboratory tasks, TwinBridge achieves a final mean autonomous success rate of 98% with at most 25 minutes of real-world interaction per task. Experiments show that dense rewards improve interaction efficiency over sparse rewards, and simulation-based policy initialization further accelerates learning.