ワールドトランスレーション:逆動力学抽出と非ペアドメイン変換によるシミュレーションと実世界のギャップ最小化
World Translation: Minimizing Sim-to-Real Gap with Backward Dynamics Extraction and Unpaired Domain Translation
シミュレーションと実世界のギャップを減らすため、観測された遷移から逆動力学で隠れた情報を抽出し、非ペアドメイン変換でシミュレーションと実世界のスタイルを変換する手法を提案。
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: Xinchen Yao, Leixin Chang, Hua Chen
分類: cs.RO
原文アブストラクト
The gap between simulation and reality remains a fundamental challenge in deploying simulation-trained robotic policies in the real world. Real-to-sim methods narrow this gap from the real side, learning transition dynamics from real data to build a more realistic digital world. Learned dynamics models are their dominant instance. Such methods, however, face a partial observability problem: the same observation may branch to different transitions due to unobservable factors. Existing methods assume these factors can be recovered from observation history. However, this may fail whenever observation history is uninformative, such as a sudden contact event with no prior warning. To address this limitation, we propose \textit{World Translation}, which exploits a complementary strength of simulators and learned dynamics. Simulators are deterministic but physically imperfect, while learned models are accurate but underdetermined under partial observability. Rather than predicting transitions forward from history, we extract the unobservable dynamics information backward from an observed transition, then translate this feature across simulation and reality as an unpaired domain-translation problem that preserves dynamics content while transferring domain style. Experiments across humanoid, quadruped, and manipulator platforms show that our method achieves more accurate dynamics modeling than baselines, with the largest gains when unobservable factors cannot be recovered from observation history. Real-robot deployment on Go2 quadruped confirms improved policy transfer.
