arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.08060cs.ROcs.SYeess.SY
收藏

从演示中学习技能:从运动原语到经验抽象的趋势

Learning Skills from Demonstrations: A Trend from Motion Primitives to Experience Abstraction

Italian Institute of Technology(意大利理工学院);Irish Manufacturing Research(爱尔兰制造研究院);University of Siena(锡耶纳大学)

Mehrdad Tavassoli, Sunny Katyara, Maria Pozzi, Nikhil Deshpande, Darwin G. Caldwell, Domenico Prattichizzo

摘要:

机器人的使用正在从工厂中的静态环境转变为包括非结构化环境中的人机协作等新概念。为机器人预编程所有功能变得不切实际,因此,机器人需要学习如何像人类一样自主地对新事件做出反应。然而,与机器不同,人类天生擅长根据经验或观察来应对意外情况。因此,将这种行为嵌入机器人需要开发神经认知模型,在机器人学习范式下模仿运动技能。这些技能的有效编码必然要选择适当的工具和技术。本文研究了不同的运动和行为学习方法,从运动原语(MP)到经验抽象(EA),适用于不同的机器人任务。这些方法进行审查,然后通过重建一个标准的pick-n-place任务实验基准。除了为策略和算法的选择提供一个标准的指导方针外,本文还旨在对其可能的扩展和改进进行展望

英文摘要:

The uses of robots are changing from static environments in factories to encompass novel concepts such as Human-Robot Collaboration in unstructured settings. Pre-programming all the functionalities for robots becomes impractical, and hence, robots need to learn how to react to new events autonomously, just like humans. However, humans, unlike machines, are naturally skilled in responding to unexpected circumstances based on either experiences or observations. Hence, embedding such anthropoid behaviours into robots entails the development of neuro-cognitive models that emulate motor skills under a robot learning paradigm. Effective encoding of these skills is bound to the proper choice of tools and techniques. This paper studies different motion and behaviour learning methods ranging from Movement Primitives (MP) to Experience Abstraction (EA), applied to different robotic tasks. These methods are scrutinized and then experimentally benchmarked by reconstructing a standard pick-n-place task. Apart from providing a standard guideline for the selection of strategies and algorithms, this paper aims to draw a perspectives on their possible extensions and improvements

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。

↑