D-REX: 巧みな把持学習のための微分可能な実世界-シミュレーション-実世界エンジン
D-REX: Differentiable Real-to-Sim-to-Real Engine for Learning Dexterous Grasping
ガウススプラット表現を用いた微分可能エンジンを構築し、実世界の視覚観測とロボット制御信号から物体質量を同定しつつ、把持ポリシーを同時学習する手法を提案。
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: Haozhe Lou, Mingtong Zhang, Haoran Geng, Hanyang Zhou, Sicheng He, Zhiyuan Gao, Siheng Zhao, Jiageng Mao, Pieter Abbeel, Jitendra Malik, Daniel Seita, Yue Wang
分類: cs.RO, cs.CV, cs.GR
原文アブストラクト
Simulation provides a cost-effective and flexible platform for data generation and policy learning to develop robotic systems. However, bridging the gap between simulation and real-world dynamics remains a significant challenge, especially in physical parameter identification. In this work, we introduce a real-to-sim-to-real engine that leverages the Gaussian Splat representations to build a differentiable engine, enabling object mass identification from real-world visual observations and robot control signals, while enabling grasping policy learning simultaneously. Through optimizing the mass of the manipulated object, our method automatically builds high-fidelity and physically plausible digital twins. Additionally, we propose a novel approach to train force-aware grasping policies from limited data by transferring feasible human demonstrations into simulated robot demonstrations. Through comprehensive experiments, we demonstrate that our engine achieves accurate and robust performance in mass identification across various object geometries and mass values. Those optimized mass values facilitate force-aware policy learning, achieving superior and high performance in object grasping, effectively reducing the sim-to-real gap.
関連論文
- GRIP: 変形可能・剛体連成把持のための汎用ロボット接触シミュレーションデータセット把持/シミュレーション
