MoEベースの頑健な四脚歩行におけるsim-to-real予測可能性の信頼性向上
Toward Reliable Sim-to-Real Predictability for MoE-based Robust Quadrupedal Locomotion
複数の専門家をゲートで切り替えるMoE歩行ポリシーと、sim-to-real転移性を予測評価するRoboGaugeを提案し、Unitree Go2で雪・砂・階段などの未見地形を安定歩行できることを示した。
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: Tianyang Wu, Hanwei Guo, Yuhang Wang, Junshu Yang, Xinyang Sui, Jiayi Xie, Xingyu Chen, Zeyang Liu, Xuguang Lan
分類: cs.RO
原文アブストラクト
Reinforcement learning has shown strong promise for quadrupedal agile locomotion, even with proprioception-only sensing. In practice, however, sim-to-real gap and reward overfitting in complex terrains can produce policies that fail to transfer, while physical validation remains risky and inefficient. To address these challenges, we introduce a unified framework encompassing a Mixture-of-Experts (MoE) locomotion policy for robust multi-terrain representation with RoboGauge, a predictive assessment suite that quantifies sim-to-real transferability. The MoE policy employs a gated set of specialist experts to decompose latent terrain and command modeling, achieving superior deployment robustness and generalization via proprioception alone. RoboGauge further provides multi-dimensional proprioception-based metrics via sim-to-sim tests over terrains, difficulty levels, and domain randomizations, enabling reliable MoE policy selection without extensive physical trials. Experiments on a Unitree Go2 demonstrate robust locomotion on unseen challenging terrains, including snow, sand, stairs, slopes, and 30 cm obstacles. In dedicated high-speed tests, the robot reaches 4 m/s and exhibits an emergent narrow-width gait associated with improved stability at high velocity.
