Generalizing Learned Manipulation Skills in Practice

Generalizing Learned Manipulation Skills in Practice
复制标题

在实践中推广所学的操作技能

DOI:
10.1109/iros45743.2020.9340739
复制
发表时间:
2020
期刊:
2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS
影响因子:
--
通讯作者:
Sun, Yu
Sun, Yu
中科院分区:
--
文献类型:
--
作者:
Wilches, Juan;Huang, Yongqiang;Sun, Yu

文献摘要

参考文献

被引文献

相似文献

机器人应该能够在不同的环境中学习和执行操纵任务。本文提出了一种从演示中学习基于RNN的操作技能模型,然后在新的环境中推广所学技能的方法。从初始设置中的演示中学习的操作技能模型在这些设置和类似的设置中表现良好。然而,该模型可能在与学习的设置显著不同的新设置中表现不佳。因此,一种新的方法被称为实践中的泛化(GIP)来解决这一关键问题。在这种方法中,机器人在新的环境中进行练习,以获得新的训练数据,并使用新的数据来提炼学习的技能,从而逐步改进学习的技能模型。所提出的方法已经在烹饪应用中执行最多的一种操作任务-浇注中得到了实现。这种方法使浇注机器人在学习的设置中能够在速度和精度方面像人一样优雅地浇注,并在经过多次练习后逐渐提高了在新设置下的浇注性能。
Robots should be able to learn and perform a manipulation task across different settings. This paper presents an approach that learns an RNN-based manipulation skill model from demonstrations and then generalizes the learned skill in new settings. The manipulation skill model learned from demonstrations in an initial set of setting performs well in those settings and similar ones. However, the model may perform poorly in a novel setting that is significantly different from the learned settings. Therefore a novel approach called generalization in practice (GiP) is developed to tackle this critical problem. In this approach, the robot practices in the new setting to obtain new training data and refine the learned skill using the new data to gradually improve the learned skill model. The proposed approach has been implemented for one type of manipulation task – pouring that is the most performed manipulation in cooking applications. The presented approach enables a pouring robot to pour gracefully like a person in terms of speed and accuracy in learned setups and gradually improve the pouring performance in novel setups after several practices.
DOI: 10.1109/icra.2017.7989307
发表时间: 2016-10
期刊: 2017 IEEE International Conference on Robotics and Automation (ICRA)
影响因子: --
作者:
Connor Schenck;D. Fox
通讯作者: Connor Schenck;D. Fox
DOI: --
发表时间: 2014
期刊: 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems
影响因子: --
作者:
Yun Lin;Yu Sun
通讯作者: Yu Sun
机器人的操纵运动分类和编码
DOI: 10.1109/iros40897.2019.8967754
发表时间: 2019
期刊: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
影响因子: --
作者:
D. Paulius;Yongqiang Huang;J. Meloncon;Yu Sun
通讯作者: Yu Sun
DOI: 10.1109/iros.2015.7354073
发表时间: 2015
期刊: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
影响因子: --
作者:
Yongqiang Huang;Yu Sun
通讯作者: Yu Sun
DOI: 10.1109/iros40897.2019.8967802
发表时间: 2019-11
期刊: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
影响因子: --
作者:
Tianze Chen;Yongqiang Huang;Yu Sun
通讯作者: Tianze Chen;Yongqiang Huang;Yu Sun