用强化学习让机器人行为树实时适应工件微小变化。
On the Fly Adaptation of Behavior Tree-Based Policies through Reinforcement Learning
- 基于行为树构建可解释的模块化控制框架。
- 在仿真与真实机械臂上实现对障碍避让等任务的快速自适应。
- 适合需要灵活响应环境变化的工业机器人场景。
随着柔性制造需求增长，机器人需在动态环境中运行，常面临工件位置偏移或尺寸差异等局部变化。本文提出一种样本高效的分层强化学习方法，用于动态调整基于行为树（BT）的策略。在保持行为树可解释性与模块化优势的同时，扩展其应用范围，使其能自然适应局部任务变化。通过在仿真环境及一台Franka Emika Panda 7-DoF机械臂上的实验，验证了该方法在不同避障和旋转任务中具备高效性与有效性。
原文摘要 · Abstract (English)
With the rising demand for flexible manufacturing, robots are increasingly expected to operate in dynamic environments where local -- such as slight offsets or size differences in workpieces -- are common. We propose to address the problem of adapting robot behaviors to these task variations with a sample-efficient hierarchical reinforcement learning approach adapting Behavior Tree (BT)-based policies. We maintain the core BT properties as an interpretable, modular framework for structuring reactive behaviors, but extend their use beyond static tasks by inherently accommodating local task variations. To show the efficiency and effectiveness of our approach, we conduct experiments both in simulation and on a Franka Emika Panda 7-DoF, with the manipulator adapting to different obstacle avoidance and pivoting tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。