Deep Deterministic Policy Gradient for Navigation of Mobile Robots

Author:

de Jesus Junior Costa1,Bottega Jair Augusto2,Cuadros Marco Antonio de Souza Leite3,Gamarra Daniel Fernando Tello4

Affiliation:

1. Federal University of Rio Grande, Rio Grande, Rio Grande do Sul, Brazil

2. Federal University of Santa Maria, Santa Maria, Rio Grande do Sul, Brazil

3. Federal Institute of Espirito Santo, Serra, Espirito Santo, Brazil

4. Processing Department of Electricity, Federal University of Santa Maria, Santa Maria, RioGrande do Sul, Brazil

Abstract

This article describes the use of the Deep Deterministic Policy Gradient network, a deep reinforcement learning algorithm, for mobile robot navigation. The neural network structure has as inputs laser range findings, angular and linear velocities of the robot, and position and orientation of the mobile robot with respect to a goal position. The outputs of the network will be the angular and linear velocities used as control signals for the robot. The experiments demonstrated that deep reinforcement learning’s techniques that uses continuous actions, are efficient for decision-making in a mobile robot. Nevertheless, the design of the reward functions constitutes an important issue in the performance of deep reinforcement learning algorithms. In order to show the performance of the Deep Reinforcement Learning algorithm, we have applied successfully the proposed architecture in simulated environments and in experiments with a real robot.

Publisher

IOS Press

Subject

Artificial Intelligence,General Engineering,Statistics and Probability

Reference6 articles.

1. Mobile robot navigation using an objectrecognition software with rgbd images and the yolo algorithm;Dos Reis;Applied Artificial Intelligence,2019

2. Fairchild C. and Harman T.L. , ROS Robotics By Example, Packt Publishing Ltd (2016).

3. Joseph L. , Mastering ROS for robotics programming, Packt Publishing Ltd (2015).

4. Human-level control through deep reinforcement learning;Mnih;Nature,2015

5. Article users activitygesture recognition on kinect sensor using convolutional neural networks and fastdtw for controlling movements ofa mobile robot;Pfitscher;Inteligencia Artificial,2019

Cited by 6 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3