Learning, Generalization, and Obstacle Avoidance with Dynamic Movement Primitives and Dynamic Potential Fields

Learning, Generalization, and Obstacle Avoidance with Dynamic Movement Primitives and Dynamic Potential Fields

In order to offer simple and convenient assistance for the elderly and disabled to take care of themselves, we propose a general learning and generalization approach for a service robot to accomplish specified tasks autonomously in an unstructured home environment. This approach firstly learns the r...

Full description

Bibliographic Details
Main Authors: Mingshan Chi, Yufeng Yao, Yaxin Liu, Ming Zhong
Format: Article
Language:English
Published: MDPI AG 2019-04-01
Series:Applied Sciences
Subjects:
service robots
dynamic motion primitives (DMPs)
dynamic potential field (DPF)
obstacle avoidance
Online Access:https://www.mdpi.com/2076-3417/9/8/1535
id doaj-4d50c5ab8c6a4510a077bba54a9869d5
record_format Article
spelling doaj-4d50c5ab8c6a4510a077bba54a9869d52020-11-25T00:49:18ZengMDPI AGApplied Sciences2076-34172019-04-0198153510.3390/app9081535app9081535Learning, Generalization, and Obstacle Avoidance with Dynamic Movement Primitives and Dynamic Potential FieldsMingshan Chi0Yufeng Yao1Yaxin Liu2Ming Zhong3State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150001, ChinaState Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150001, ChinaState Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150001, ChinaState Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150001, ChinaIn order to offer simple and convenient assistance for the elderly and disabled to take care of themselves, we propose a general learning and generalization approach for a service robot to accomplish specified tasks autonomously in an unstructured home environment. This approach firstly learns the required tasks by learning from demonstration (LfD) and represents the learned tasks with dynamic motion primitives (DMPs), so as to easily generalize them to a new environment only with little modification. Furthermore, we integrate dynamic potential field (DPF) with the above DMPs model to realize the autonomous obstacle avoidance function of a service robot. This approach is validated on the wheelchair mounted robotic arm (WMRA) by performing serial experiments of placing a cup on the table with an obstacle or without obstacle on its motion path.https://www.mdpi.com/2076-3417/9/8/1535service robotsdynamic motion primitives (DMPs)dynamic potential field (DPF)obstacle avoidance
collection DOAJ
language English
format Article
sources DOAJ
author Mingshan Chi
Yufeng Yao
Yaxin Liu
Ming Zhong
spellingShingle Mingshan Chi
Yufeng Yao
Yaxin Liu
Ming Zhong
Learning, Generalization, and Obstacle Avoidance with Dynamic Movement Primitives and Dynamic Potential Fields
Applied Sciences
service robots
dynamic motion primitives (DMPs)
dynamic potential field (DPF)
obstacle avoidance
author_facet Mingshan Chi
Yufeng Yao
Yaxin Liu
Ming Zhong
author_sort Mingshan Chi
title Learning, Generalization, and Obstacle Avoidance with Dynamic Movement Primitives and Dynamic Potential Fields
title_short Learning, Generalization, and Obstacle Avoidance with Dynamic Movement Primitives and Dynamic Potential Fields
title_full Learning, Generalization, and Obstacle Avoidance with Dynamic Movement Primitives and Dynamic Potential Fields
title_fullStr Learning, Generalization, and Obstacle Avoidance with Dynamic Movement Primitives and Dynamic Potential Fields
title_full_unstemmed Learning, Generalization, and Obstacle Avoidance with Dynamic Movement Primitives and Dynamic Potential Fields
title_sort learning, generalization, and obstacle avoidance with dynamic movement primitives and dynamic potential fields
publisher MDPI AG
series Applied Sciences
issn 2076-3417
publishDate 2019-04-01
description In order to offer simple and convenient assistance for the elderly and disabled to take care of themselves, we propose a general learning and generalization approach for a service robot to accomplish specified tasks autonomously in an unstructured home environment. This approach firstly learns the required tasks by learning from demonstration (LfD) and represents the learned tasks with dynamic motion primitives (DMPs), so as to easily generalize them to a new environment only with little modification. Furthermore, we integrate dynamic potential field (DPF) with the above DMPs model to realize the autonomous obstacle avoidance function of a service robot. This approach is validated on the wheelchair mounted robotic arm (WMRA) by performing serial experiments of placing a cup on the table with an obstacle or without obstacle on its motion path.
topic service robots
dynamic motion primitives (DMPs)
dynamic potential field (DPF)
obstacle avoidance
url https://www.mdpi.com/2076-3417/9/8/1535
work_keys_str_mv AT mingshanchi learninggeneralizationandobstacleavoidancewithdynamicmovementprimitivesanddynamicpotentialfields
AT yufengyao learninggeneralizationandobstacleavoidancewithdynamicmovementprimitivesanddynamicpotentialfields
AT yaxinliu learninggeneralizationandobstacleavoidancewithdynamicmovementprimitivesanddynamicpotentialfields
AT mingzhong learninggeneralizationandobstacleavoidancewithdynamicmovementprimitivesanddynamicpotentialfields
_version_ 1725251795193692160

Similar Items