完全な専門家データセット不要の四足ロボット多様スキル連続制御
Continuous Control of Diverse Skills in Quadruped Robots Without Complete Expert Datasets
専門家のデモンストレーションなしで、目標姿勢に基づき自己模倣と敵対的学習により四足ロボットの多様なスキルとその滑らかな遷移を獲得する手法を提案。
著者: Jiaxin Tu, Xiaoyi Wei, Yueqi Zhang, Taixian Hou, Xiaofei Gao, Zhiyan Dong, Peng Zhai, Lihua Zhang
分類: cs.RO
原文アブストラクト
Learning diverse skills for quadruped robots presents significant challenges, such as mastering complex transitions between different skills and handling tasks of varying difficulty. Existing imitation learning methods, while successful, rely on expensive datasets to reproduce expert behaviors. Inspired by introspective learning, we propose Progressive Adversarial Self-Imitation Skill Transition (PASIST), a novel method that eliminates the need for complete expert datasets. PASIST autonomously explores and selects high-quality trajectories based on predefined target poses instead of demonstrations, leveraging the Generative Adversarial Self-Imitation Learning (GASIL) framework. To further enhance learning, We develop a skill selection module to mitigate mode collapse by balancing the weights of skills with varying levels of difficulty. Through these methods, PASIST is able to reproduce skills corresponding to the target pose while achieving smooth and natural transitions between them. Evaluations on both simulation platforms and the Solo 8 robot confirm the effectiveness of PASIST, offering an efficient alternative to expert-driven learning.
