Path Planning using DDPG Algorithm and Univector Field Method for Intelligent Mobile Robot

Year : 2024 | Volume :02 | Issue : 02 | Page : 1-9
By
vector

Jiyon Yun,

vector

Kangsong Ro,

vector

Jusong Pak,

vector

Choljin Wang,

  1. Student, Department of Mechanical Engineering, Kim Chaek University of Technology, Pyongyang, DPR Korea, Korea
  2. Student, Department of Mechanical Engineering, Kim Chaek University of Technology, Pyongyang, DPR Korea, Korea
  3. Student, Department of Mechanical Engineering, Kim Chaek University of Technology, Pyongyang, DPR Korea, Korea
  4. Student, Department of Mechanical Engineering, Kim Chaek University of Technology, Pyongyang, DPR Korea, Korea

Abstract document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_abs_127223’);});Edit Abstract & Keyword

Path planning is one of the most fundamental challenging tasks in robotics and its purpose is to lead the robot from the initial position to the goal without any collision through the optimal route. With the rapid development of artificial intelligence technology, AI has been widely studied for robot path planning and a method by deep reinforcement learning (DRL) was proposed. In general, path planning methods with DRL need discrete action space and use deep Q-network (DQN). Real robot moves in continuous action space, so discontinuity of it may cause impossibility of optimization of path planning and some serious problems in combination with dynamics of the robot. Enhancing the action dimension can be used to work out this problem, but significantly increases the calculation time. In order to dispose of the issue and the optimal path planning, a new method to consider the action space of the robot as an continuous space by combination between univector field method (UVFM) and DDPG which is one of the popular reinforcement learning algorithms was proposed in this paper. Simulation results show possibility and efficiency of the proposed path planning method.

Keywords: DDPG Algorithm, univector field method, continuous action space, APFM

[This article belongs to International Journal of Advanced Robotics and Automation Technology (ijarat)]

How to cite this article:
Jiyon Yun, Kangsong Ro, Jusong Pak, Choljin Wang. Path Planning using DDPG Algorithm and Univector Field Method for Intelligent Mobile Robot. International Journal of Advanced Robotics and Automation Technology. 2024; 02(02):1-9.
How to cite this URL:
Jiyon Yun, Kangsong Ro, Jusong Pak, Choljin Wang. Path Planning using DDPG Algorithm and Univector Field Method for Intelligent Mobile Robot. International Journal of Advanced Robotics and Automation Technology. 2024; 02(02):1-9. Available from: https://journals.stmjournals.com/ijarat/article=2024/view=0

Full Text PDF

Full Text PDF

References
document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_ref_127223’);});Edit

  1. Xianxia Liang, Zhaoying Liu, Xueling Song, Yngkun Zhang, “Research on Improved Artificial Potential Field
  2. Approach in Local Path Planning for Mobile Robot. Computer Simulation”, 2018
  3. Liu Cuodong, Xie Hong-bin, Li Chunguang, “Method of mobile robot path planning in dynamic environment based on genetic algorirthm [J]. Robot”, 2003
  4. Bingbing Xu, Rongfei Hao, “Current Situation and Development of Robot Path Planning Technology. Electronic Technology & Software Engineering”, 2019
  5. Yifan Guo and Zhiping Liu, “UAV Path Planning Based on Deep Reinforcement Learning”, 2023
  6. Jeevan Raajan, Srihari P V, Satya Jayadev P, B Bhikkaji and Ramkrishna Pasumarthy, “Real Time Path Planning of Robot using Deep Reinforcement Learning”, 2020
  7. Sudharsan Ravichandiran, “Deep Reinforcement Learning with Python”, 2020
  8. Phalgun Chintala, Rolf Dornberger and Thomas Hanne, “Robotic Path Planning by Q Learning and a performance Comparison with Classical Path Finding Algorithms”, 2022
  9. Li S., Xin X., and Lei Z., “Dynamic path planning of a mobile robot with improved Q-learning algorithm”, 2015
  10. Zhen Shi, Keyin Wang, Jianhui Zhang “Improved reinforcement learning path planning algorithm integrating prior knowledge”, 2023
  11. Li S., Xin X., and Lei Z., “Dynamic path planning of a mobile robot with improved Q-learning algorithm”, 2015
  12. Noor H. Fallooh, Ahmed T. Sadiq, Eyad I. Abbas & Ivan A. hashim, “Dynamic Path Planning using a modification Q-Learning Algorithm for a Mobile Robot”,2024
  13. Xuemei He, Yin Kuang, Ning Song, Fan Liu, “Intelligent Navigation of Indoor Robot Based on Improved DDPG Algorithm”,2023
Regular Issue Subscription Review Article
Volume 02
Issue 02
Received 12/07/2024
Accepted 20/10/2024
Published 10/12/2024
193