利用子策略间的不一致性学习仲裁人与机器人控制
Learning to Arbitrate Human and Robot Control using Disagreement between Sub-Policies
摘要:
在远程操作的背景下,仲裁是指决定如何混合人类和自主机器人命令。我们提出了一个强化学习解决方案,学习一个最佳的仲裁策略,分配更多的控制权时,机器人在任务中遇到的决策点的人。决策点是机器人遇到多个选项(子策略)的地方,例如有多条路径绕过障碍物或在两个候选目标之间做出决定。通过将每个方向子策略表示为冯米塞斯分布,我们通过观察混合分布的模态来识别决策点。我们的奖励函数基于这种模式进行推理,并相应地将其学习的策略与用户或机器人相匹配。我们报告的遥操作实验达到和掌握的对象,使用不同的模拟人类控制器的机器人机械臂。结果表明,我们的共享控制代理优于直接控制,提高了不同用户之间的遥操作性能。使用我们的奖励条件可以在人类和机器人命令之间灵活混合,同时保持安全和准确的远程操作。
英文摘要:
In the context of teleoperation, arbitration refers to deciding how to blend between human and autonomous robot commands. We present a reinforcement learning solution that learns an optimal arbitration strategy that allocates more control authority to the human when the robot comes across a decision point in the task. A decision point is where the robot encounters multiple options (sub-policies), such as having multiple paths to get around an obstacle or deciding between two candidate goals. By expressing each directional sub-policy as a von Mises distribution, we identify the decision points by observing the modality of the mixture distribution. Our reward function reasons on this modality and prioritizes to match its learned policy to either the user or the robot accordingly. We report teleoperation experiments on reach-and-grasping objects using a robot manipulator arm with different simulated human controllers. Results indicate that our shared control agent outperforms direct control and improves the teleoperation performance among different users. Using our reward term enables flexible blending between human and robot commands while maintaining safe and accurate teleoperation.
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。