Research on Dynamic Path Planning of Mobile Robot Based on Improved DDPG Algorithm

被引：23

作者：

Li, Peng ^{[1
]}

Ding, Xiangcheng ^{[1
]}

Sun, Hongfang ^{[2
]}

Zhao, Shiquan ^{[1
]}

Cajo, Ricardo ^{[3
,4
]}

机构：

[1] Harbin Engn Univ, Coll Intelligent Sci & Engn, Harbin, Heilongjiang, Peoples R China

[2] Harbin Engn Univ, Qingdao Ship Sci & Technol Co Ltd, Harbin, Shandong, Peoples R China

[3] Univ Ghent, Dept Elect Syst & Met Engn, Ghent, Belgium

[4] Escuela Super Politecn Litoral ESPOL, Fac Ingn Elect & Computac, Guayaquil, Ecuador

来源：

MOBILE INFORMATION SYSTEMS | 2021年 / 2021卷

关键词：

21;

D O I：

10.1155/2021/5169460

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Aiming at the problems of low success rate and slow learning speed of the DDPG algorithm in path planning of a mobile robot in a dynamic environment, an improved DDPG algorithm is designed. In this article, the RAdam algorithm is used to replace the neural network optimizer in DDPG, combined with the curiosity algorithm to improve the success rate and convergence speed. Based on the improved algorithm, priority experience replay is added, and transfer learning is introduced to improve the training effect. Through the ROS robot operating system and Gazebo simulation software, a dynamic simulation environment is established, and the improved DDPG algorithm and DDPG algorithm are compared. For the dynamic path planning task of the mobile robot, the simulation results show that the convergence speed of the improved DDPG algorithm is increased by 21%, and the success rate is increased to 90% compared with the original DDPG algorithm. It has a good effect on dynamic path planning for mobile robots with continuous action space.

引用

页数：10

共 21 条

[1] Guest editorial: Machine learning in wireless networks [J].

Budati, Anil Kumar ;

Ling, Steve S. H. .

CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY, 2021, 6 (02) :133-134

[2]

Chen Q, 2018, CHIN CONT DECIS CONF, P2710, DOI 10.1109/CCDC.2018.8407585

[3] An adapted ant colony optimization algorithm for the minimization of the travel distance of pickers in manual warehouses [J].

De Santis, Roberta ;

Montanari, Roberto ;

Vignali, Giuseppe ;

Bottani, Eleonora .

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2018, 267 (01) :120-137

[4]

Dong YS, 2020, INT CONF SOFTW ENG, P52, DOI [10.1109/ICISCE50968.2020.00021, 10.1109/icsess49938.2020.9237641, 10.1109/ICSESS49938.2020.9237641]

[5] Research on the Path Planning Algorithm of Mobile Robot [J].

Gao, Yingding ;

Hu, Tianyang ;

Wang, Yinchu ;

Zhang, Yang .

2021 13TH INTERNATIONAL CONFERENCE ON MEASURING TECHNOLOGY AND MECHATRONICS AUTOMATION (ICMTMA 2021), 2021, :447-450

[6]

Huang H, 2019, PROCEEDINGS OF 2019 IEEE 3RD INFORMATION TECHNOLOGY, NETWORKING, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (ITNEC 2019), P1121, DOI [10.1109/ITNEC.2019.8729438, 10.1109/itnec.2019.8729438]

[7] Path planning for intelligent robots based on deep Q-learning with experience replay and heuristic knowledge [J].

Jiang, Lan ;

Huang, Hongyun ;

Ding, Zuohua .

IEEE-CAA JOURNAL OF AUTOMATICA SINICA, 2020, 7 (04) :1179-1189

[8]

Ke Cui, 2020, 2020 International Conference on Computer Engineering and Application (ICCEA), P468, DOI 10.1109/ICCEA50009.2020.00107

[9] Socially compliant mobile robot navigation via inverse reinforcement learning [J].

Kretzschmar, Henrik ;

Spies, Markus ;

Sprunk, Christoph ;

Burgard, Wolfram .

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2016, 35 (11) :1352-1370

[10] An Adaptive Online Co-Search Method With Distributed Samples for Dynamic Target Tracking [J].

Li, Feng ;

Zhou, Mengchu ;

Ding, Yongsheng .

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2018, 26 (02) :439-451

← 1 2 3 →