データ駆動型物理埋め込みダイナミクスと予測制御・強化学習による四足歩行
Data-Driven Physics Embedded Dynamics with Predictive Control and Reinforcement Learning for Quadrupeds
ラグランジュニューラルネットワークを強化学習とモデル予測制御に統合し、四足歩行の物理的に整合したダイナミクス学習と効率的な実時間計画を実現した。
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: Prakrut Kotecha, Aditya Shirwatkar, Shishir Kolathaya
分類: cs.RO, cs.LG
原文アブストラクト
State of the art quadrupedal locomotion approaches integrate Model Predictive Control (MPC) with Reinforcement Learning (RL), enabling complex motion capabilities with planning and terrain adaptive behaviors. However, they often face compounding errors over long horizons and have limited interpretability due to the absence of physical inductive biases. We address these issues by integrating Lagrangian Neural Networks (LNNs) into an RL MPC framework, enabling physically consistent dynamics learning. At deployment, our inverse dynamics infinite horizon MPC scheme avoids costly matrix inversions, improving computational efficiency by up to 4x with minimal loss of task performance. We validate our framework through multiple ablations of the proposed LNN and its variants. We show improved sample efficiency, reduced long-horizon error, and faster real time planning compared to unstructured neural dynamics. Lastly, we also test our framework on the Unitree Go1 robot to show real world viability.
