Towards Motor Skill Learning for Robotics
Towards Motor Skill Learning for Robotics
复制标题
走向机器人运动技能学习
DOI：
--
复制
发表时间：
2007
期刊：
影响因子：
--
通讯作者：
Oliver Kroemer
中科院分区：
文献类型：
--
作者：
Jan Peters;Katharina Muelling;Jens Kober;D. Nguyen;Oliver Kroemer
学习机器人能够获得新的运动技能并完善现有的运动技能一直是机器人学、人工智能和认知科学的长期愿景。 20 世纪 80 年代实现这一目标的早期步骤清楚地表明，推理和人类洞察力是不够的。相反，现代机器学习方法的兴起带来了新的希望。然而，迄今为止，越来越明显的是，现成的机器学习方法不足以用于运动技能学习，因为这些方法通常不能扩展到机械手和人形机器人的高维领域，也不能满足我们领域的实时要求。作为替代方案，我们建议将通用技能学习问题分解为我们可以从机器人学角度很好理解的部分。在为这些基本组成部分设计适当的学习方法后，这些将作为运动技能学习通用方法的要素。在本文中，我们讨论了我们在这个方向上最近和当前的进展。为此，我们介绍了我们在学习控制、学习基本动作以及学习复杂任务的步骤方面的工作。我们展示了使用真实机器人和物理真实模拟进行的多项评估。
Learning robots that can acquire new motor skills and refine existing one has been a long standing vision of robotics, artificial intelligence, and the cognitive sciences. Early steps towards this goal in the 1980s made clear that reasoning and human insights will not suffice. Instead, new hope has been offered by the rise of modern machine learning approaches. However, to date, it becomes increasingly clear that off-the-shelf machine learning approaches will not suffice for motor skill learning as these methods often do not scale into the high-dimensional domains of manipulator and humanoid robotics nor do they fulfill the real-time requirement of our domain. As an alternative, we propose to break the generic skill learning problem into parts that we can understand well from a robotics point of view. After designing appropriate learning approaches for these basic components, these will serve as the ingredients of a general approach to motor skill learning. In this paper, we discuss our recent and current progress in this direction. For doing so, we present our work on learning to control, on learning elementary movements as well as our steps towards learning of complex tasks. We show several evaluations both using real robots as well as physically realistic simulations.