arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2205.13441cs.ROcs.AI
收藏

基于自适应分层课程的多阶段多目标灵巧操作

Multi-Phase Multi-Objective Dexterous Manipulation with Adaptive Hierarchical Curriculum

Colorado School of Mines(科罗拉多矿业学院);GAC R&D Center Silicon Valley(广汽研发中心硅谷分部)

Lingfeng Tao, Jiucai Zhang, Xiaoli Zhang

AI总结:

针对灵巧操作中多目标优先级随阶段变化导致深度强化学习困难的问题,提出自适应分层奖励机制(AHRM),动态确定目标优先级并更新奖励分层,在JACO机械臂实验中显著提升了任务性能与学习效率。

摘要:

灵巧操作任务通常具有多个目标,且这些目标的优先级在操作任务的不同阶段可能会发生变化。变化的优先级使得机器人难以甚至无法通过深度强化学习(DRL)方法学习到最优策略。为解决这一问题,我们开发了一种新颖的自适应分层奖励机制(AHRM),以引导DRL智能体学习具有多个优先级目标的操作任务。AHRM能够在学习过程中确定目标优先级,并更新奖励分层以适应不同阶段不断变化的目标优先级。所提出的方法在JACO机械臂的多目标操作任务中得到了验证,该任务要求机器人在周围有障碍物的情况下操作目标。仿真和物理实验结果表明,所提出的方法在任务性能和学习效率上均提升了机器人学习效果。

英文摘要:

Dexterous manipulation tasks usually have multiple objectives, and the priorities of these objectives may vary at different phases of a manipulation task. Varying priority makes a robot hardly or even failed to learn an optimal policy with a deep reinforcement learning (DRL) method. To solve this problem, we develop a novel Adaptive Hierarchical Reward Mechanism (AHRM) to guide the DRL agent to learn manipulation tasks with multiple prioritized objectives. The AHRM can determine the objective priorities during the learning process and update the reward hierarchy to adapt to the changing objective priorities at different phases. The proposed method is validated in a multi-objective manipulation task with a JACO robot arm in which the robot needs to manipulate a target with obstacles surrounded. The simulation and physical experiment results show that the proposed method improved robot learning in task performance and learning efficiency.

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。

↑