運動プリエアを用いた潜在条件付き移動操作
Latent Conditioned Loco-Manipulation Using Motion Priors
人間型・四足ロボットの移動操作において、模倣学習で多目的運動ポリシーを訓練し、潜在空間制御で下流タスクを効率的に解く手法を提案。拡散識別器と制約処理で安全性と模倣品質を向上。
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: Maciej Stępień, Rafael Kourdis, Constant Roux, Olivier Stasse
分類: cs.RO
原文アブストラクト
Although humanoid and quadruped robots provide a wide range of capabilities, current control methods, such as Deep Reinforcement Learning, focus mainly on single skills. This approach is inefficient for solving more complicated tasks where high-level goals, physical robot limitations and desired motion style might all need to be taken into account. A more effective approach is to first train a multipurpose motion policy that acquires low-level skills through imitation, while providing latent space control over skill execution. Then, this policy can be used to efficiently solve downstream tasks. This method has already been successful for controlling characters in computer graphics. In this work, we apply the approach to humanoid and quadrupedal loco-manipulation by imitating either simple synthetic motions or kinematically retargeted dog motions. We extend the original formulation to handle constraints, ensuring deployment safety, and use a diffusion discriminator for better imitation quality. We verify our methods by performing loco-manipulation in simulation for the H1 humanoid and Solo12 quadruped, as well as deploying policies on Solo12 hardware. Videos and code are available at https://gepetto.github.io/LaCoLoco/
