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 2402.13466cs.RO
收藏

利用演示者感知精度实现间隙受限任务的安全交互式模仿学习

Leveraging Demonstrator-perceived Precision for Safe Interactive Imitation Learning of Clearance-limited Tasks

Nara Institute of Science and Technology(奈良科学技术研究所)

Hanbit Oh, Takamitsu Matsubara

AI总结:

针对间隙受限任务中交互式模仿学习的安全问题,本文提出 DPIIL 方法,利用人类演示中的速度-精度权衡感知环境精度,在高风险状态让渡控制权给人类,从而在无需显式环境模型的情况下提升训练安全性,并通过仿真和 UR5e 机械臂装配实验验证了其有效性。

摘要:

交互式模仿学习是一种高效的免模型方法,机器人通过反复迭代执行学习策略和查询人类演示来收集数据,从而学习任务。然而,对于工业插入等间隙受限任务,部署未成熟策略会带来显著的碰撞风险。对于此类任务,机器人应检测碰撞风险,并在碰撞即将发生时通过将控制权让渡给人类来请求干预。前者需要准确的环境模型,这一需求极大地限制了交互式模仿学习(IIL)的应用范围。相比之下,人类在执行任务时会通过调整行为来避免碰撞,从而隐式地展示环境精度。受人类行为启发,本文提出了一种新颖的交互式学习方法,该方法使用演示者感知精度作为人类干预的准则,称为演示者感知精度感知的交互式模仿学习(DPIIL)。DPIIL 通过观察人类演示中表现出的速度-精度权衡来捕获精度,并在估计为高精度的状态下将控制权让渡给人类以避免碰撞。DPIIL 提高了交互式策略学习的安全性,并在不显式提供环境精确信息的情况下确保效率。我们通过仿真和真实机器人实验评估了 DPIIL 的有效性,实验中训练了一台 UR5e 六自由度机械臂执行装配任务。我们的结果显著提高了训练安全性,并且我们的最佳性能与其他学习方法相比具有优势。

英文摘要:

Interactive imitation learning is an efficient, model-free method through which a robot can learn a task by repetitively iterating an execution of a learning policy and a data collection by querying human demonstrations. However, deploying unmatured policies for clearance-limited tasks, like industrial insertion, poses significant collision risks. For such tasks, a robot should detect the collision risks and request intervention by ceding control to a human when collisions are imminent. The former requires an accurate model of the environment, a need that significantly limits the scope of IIL applications. In contrast, humans implicitly demonstrate environmental precision by adjusting their behavior to avoid collisions when performing tasks. Inspired by human behavior, this paper presents a novel interactive learning method that uses demonstrator-perceived precision as a criterion for human intervention called Demonstrator-perceived Precision-aware Interactive Imitation Learning (DPIIL). DPIIL captures precision by observing the speed-accuracy trade-off exhibited in human demonstrations and cedes control to a human to avoid collisions in states where high precision is estimated. DPIIL improves the safety of interactive policy learning and ensures efficiency without explicitly providing precise information of the environment. We assessed DPIIL's effectiveness through simulations and real-robot experiments that trained a UR5e 6-DOF robotic arm to perform assembly tasks. Our results significantly improved training safety, and our best performance compared favorably with other learning methods.

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。

↑