A novel deep learning driven robot path planning strategy: Q-learning approach

被引:4
作者
Hu, Junli [1 ]
机构
[1] Henan Ind & Trade Vocat Coll, Zhengzhou, Peoples R China
关键词
robot; path planning; deep learning; DQN; memory;
D O I
10.1504/IJCAT.2023.132100
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
As the basis of mobile navigation technology, path planning has attracted the attention of the majority of scholars. In this paper, the deep learning framework is integrated into Q-learning, and a Deep Q-Network (DQN) algorithm based on memory optimised mechanism is designed to improve the convergence of DQN, so that the robot can carry out good path planning in complex environment. Experimental results show that the proposed method has a good performance in path planning. Experimental results show that in the case of multi-round training using the algorithm proposed in this paper, the path planning steps of the robot are the shortest and the total training time and single round time of the robot in path planning are also the shortest.
引用
收藏
页码:237 / 243
页数:8
相关论文
共 18 条
[1]   Multi-Robot Hybrid Coverage Path Planning for 3D Reconstruction of Large Structures [J].
Almadhoun, Randa ;
Taha, Tarek ;
Seneviratne, Lakmal ;
Zweiri, Yahya .
IEEE ACCESS, 2022, 10 :2037-2050
[2]   Skill-based curiosity for intrinsically motivated reinforcement learning [J].
Bougie, Nicolas ;
Ichise, Ryutaro .
MACHINE LEARNING, 2020, 109 (03) :493-512
[3]   Path planning and control of soccer robot based on genetic algorithm [J].
Chen, Xuanang ;
Gao, Peijun .
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2020, 11 (12) :6177-6186
[4]   Intelligent Traffic Signal Phase Distribution System Using Deep Q-Network [J].
Joo, Hyunjin ;
Lim, Yujin .
APPLIED SCIENCES-BASEL, 2022, 12 (01)
[5]   Time-efficient path planning using two virtual robots [J].
Kim, Jonghoek .
INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS, 2019, 16 (06)
[6]   Bias-Corrected Q-Learning With Multistate Extension [J].
Lee, Donghun ;
Powell, Warren B. .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2019, 64 (10) :4011-4023
[7]   Path Planning Based on ADFA* Algorithm for Quadruped Robot [J].
Li Zhe ;
Li Yibin ;
Rong Xuewen ;
Zhang Hui .
IEEE ACCESS, 2019, 7 :111095-111101
[8]   Learning proactive behavior for interactive social robots [J].
Liu, Phoebe ;
Glas, Dylan F. ;
Kanda, Takayuki ;
Ishiguro, Hiroshi .
AUTONOMOUS ROBOTS, 2018, 42 (05) :1067-1085
[9]   Deep Cascade Learning [J].
Marquez, Enrique S. ;
Hare, Jonathon S. ;
Niranjan, Mahesan .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (11) :5475-5485
[10]   Scalable Coverage Path Planning for Cleaning Robots Using Rectangular Map Decomposition on Large Environments [J].
Miao, Xu ;
Lee, Jaesung ;
Kang, Bo-Yeong .
IEEE ACCESS, 2018, 6 :38200-38215