面向关节物体操作的子空间混合强化学习
Subspace-wise Hybrid RL for Articulated Object Manipulation
AI总结：
针对关节物体操作中全任务空间策略学习难的问题，提出SwRL框架，按独立目标为各子空间学习策略，利用冗余子空间提升机器人灵巧性，经仿真和实物实验验证可同时提高学习效率与任务表现。
摘要：
关节物体操作是一项具有挑战性的任务，需要受约束的运动和自适应控制来应对被操作物体的未知动力学特性。尽管强化学习（RL）已被广泛用于处理各种场景和类型的关节物体，但这些任务因多个相互交织的目标而产生的复杂性，使得在完整任务空间中学习控制策略极具难度。为解决这一问题，我们提出了子空间混合RL（SwRL，Subspace-wise hybrid RL）框架，该框架基于独立目标为每个划分后的任务空间（即子空间）学习策略。该方法能够实现自适应力调制，以适配物体的未知动力学特性。此外，它有效利用了此前被忽视的冗余子空间，从而最大化机器人的灵巧性。仿真和真实世界实验均验证了我们的方法既提升了学习效率，也改善了任务执行性能。补充视频可在https://youtu.be/PkNxv0P8Atk查看。
英文摘要：
Articulated object manipulation is a challenging task, requiring constrained motion and adaptive control to handle the unknown dynamics of the manipulated objects. While reinforcement learning (RL) has been widely employed to tackle various scenarios and types of articulated objects, the complexity of these tasks, stemming from multiple intertwined objectives makes learning a control policy in the full task space highly difficult. To address this issue, we propose a Subspace-wise hybrid RL (SwRL) framework that learns policies for each divided task space, or subspace, based on independent objectives. This approach enables adaptive force modulation to accommodate the unknown dynamics of objects. Additionally, it effectively leverages the previously underlooked redundant subspace, thereby maximizing the robot's dexterity. Our method enhances both learning efficiency and task execution performance, as validated through simulations and real-world experiments. Supplementary video is available at https://youtu.be/PkNxv0P8Atk
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
