PvP: 固有感覚と特権情報の対照表現によるデータ効率の良いヒューマノイドロボット学習
PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representations
固有感覚状態と特権状態の相補性を活かした対照学習で、ヒューマノイドの全身制御を少ないデータで効率的に学習する手法を提案し、評価用フレームワークも構築した。
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: Mingqi Yuan, Tao Yu, Haolin Song, Bo Li, Xin Jin, Hua Chen, Wenjun Zeng
分類: cs.RO, cs.LG
原文アブストラクト
Achieving efficient and robust whole-body control (WBC) is essential for enabling humanoid robots to perform complex tasks in dynamic environments. Despite the success of reinforcement learning (RL) in this domain, its sample inefficiency remains a significant challenge due to the intricate dynamics and partial observability of humanoid robots. To address this limitation, we propose PvP, a Proprioceptive-Privileged contrastive learning framework that leverages the intrinsic complementarity between proprioceptive and privileged states. PvP learns compact and task-relevant latent representations without requiring hand-crafted data augmentations, enabling faster and more stable policy learning. To support systematic evaluation, we develop SRL4Humanoid, the first unified and modular framework that provides high-quality implementations of representative state representation learning (SRL) methods for humanoid robot learning. Extensive experiments on the LimX Oli robot across velocity tracking and motion imitation tasks demonstrate that PvP significantly improves sample efficiency and final performance compared to baseline SRL methods. Our study further provides practical insights into integrating SRL with RL for humanoid WBC, offering valuable guidance for data-efficient humanoid robot learning.
