In recent years, with the rapid development of artificial intelligence, many innovative changes have been made in the field of intelligent mobile robot development. In the field of control and navigation of mobile robots, learning-based methods have many advantages over traditional ones. The study of mobile robot control methods using deep reinforcement learning is a remarkable area in the development of mobile robots that must operate in dynamic environments. In the previous studies, the proposed robot control algorithms using deep reinforcement learning are mostly based on the given target point and obstacle information, the robot path planning is performed, and the corresponding control is based on the obtained path. The DDPG-based method is a typical example. However, in dynamic environments, DRL based robot path planning requires a state of target point and obstacles information, which leads to a large amount of computation, resulting in extremely long convergence time and even non-convergent cases. In this paper, we propose a new method for mobile robot control in dynamic environment that solves the dimensional problem by extracting the features of the configuration of obstacles using autoencoder and learning the DDPG algorithm based on the obtained features. Simulation results show that the proposed algorithm can effectively solve the mobile robot control problem in dynamic environment.
| Published in | International Journal of Industrial and Manufacturing Systems Engineering (Volume 10, Issue 3) |
| DOI | 10.11648/j.ijimse.20251003.11 |
| Page(s) | 44-52 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2025. Published by Science Publishing Group |
DDPG Algorithm, Autoencoder, Mobile Robot, Path Planning, Dynamic Environment
| [1] | Ashleigh S, Silvia F. A Cell Decomposition Approach to Cooperative Path Planning and Collision Avoidance via Disjunctive Programming. 49th IEEE Conference on Decision and Control; 2010 Dec 15-17; Atlanta, USA; 2011. 6329-8 p. |
| [2] | Christoph Oberndorfer. Research on new Artificial Intelligence based Path Planning Algorithms with Focus on Autonomous Driving [PhM Thesis]. Munich: University of Applied Sciences Munich; 2017. |
| [3] | Koren Y, Borenstein J. Potential Field Methods and Their Inherent Limitations for Mobile Robot Navigation. Proceedings of the IEEE Conference on Robotics and Automation; 1991 Apr 7-12; California, USA; 1991. 1398-6 p. |
| [4] | Arora T, Gigras Y, Arora V. Robotic Path Planning using Genetic Algorithm in Dynamic Environment. IJCA 2014; 89(11): 8-5 p. |
| [5] | Mahadevi S, Shylaja KR, Ravinandan ME. Memory Based A-Star Algorithm for Path Planning of a Mobile Robot. IJSR 2014; 3(6): 1351-5 p. |
| [6] | Yu ZN, Duan P, Meng LL, et al. Multi-objective path planning for mobile robot with an improved artificial bee colony algorithm. MBE 2022; 20(2): 2501-9 p. |
| [7] | Ren Y, Liu JY. Automatic Obstacle Avoidance Path Planning Method for Unmanned Ground Vehicle Based on Improved Bee Colony Algorithm. JJMIE 2022; 16(1): 11-8 p. |
| [8] | Sat C, Dayal RP. Navigational control strategy of humanoid robots using average fuzzy-neuro-genetic hybrid technique. IRAJ 2022; 8(1): 22-4 p. |
| [9] | Jeevan R, Srihari PV, Satya JP, et al. Real Time Path Planning of Robot using Deep Reinforcement Learning. Preprints of the 21st IFAC World Congress (Virtual); July 12-17, 2020; Berlin, Germany; 2020. 15811-6 p. |
| [10] | Shi YM, Zhang ZY. Research on Path Planning Strategy of Rescue Robot Based on Reinforcement Learning. Journal of Computers 2022; 33(3): 187-8 p. |
| [11] | Lucia L, Daniel D, Gianluca C, et al. Robot Navigation in Crowded Environments Using Deep Reinforcement Learning. 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)(Virtual); October 25-29, 2020; Las Vegas, NV, USA; 2020. 5671-7 p. |
| [12] | Phalgun C, Rolf D, Thomas H. Robotic Path Planning by Q Learning and a Performance Comparison with Classical Path Finding Algorithms. IJMERR 2022; 11(6): 373-6 p. |
| [13] | Yang Y, Li JT, Peng LL. Multi-robot path planning based on a deep reinforcement learning DQN algorithm. CAAI Trans. Intell. Technol 2020; 5(3): 177-7 p. |
| [14] | Zhu AY, Dai TH, Xu GY, et al. Deep Reinforcement Learning for Real-Time Assembly Planning in Robot-Based Prefabricated Construction. IEEE Trans. Auto. Sci. Technol 2023; 20(3): 1515-12 p. |
| [15] | Chen Jiong. Chonstruction of an Intelligent Robot Path Recognition System Supported by Deep Learning Network algorithms. IJACSA 2023; 14(10): 172-10 p. |
| [16] | Yun JY, Ro KS, Pak JS, et al. Path Planning using DDPG Algorithm and Univector Field Method for Intelligent Mobile Robot. IJARAT 2024; 2(2): 7-11 p. |
APA Style
Bom, C. R., Rim, P. M., Song, R. K., Bin, J. K., Yon, Y. J. (2025). Mobile Robot Control Using Deep Reinforcement Learning and Autoencoder in Dynamic Environment. International Journal of Industrial and Manufacturing Systems Engineering, 10(3), 44-52. https://doi.org/10.11648/j.ijimse.20251003.11
ACS Style
Bom, C. R.; Rim, P. M.; Song, R. K.; Bin, J. K.; Yon, Y. J. Mobile Robot Control Using Deep Reinforcement Learning and Autoencoder in Dynamic Environment. Int. J. Ind. Manuf. Syst. Eng. 2025, 10(3), 44-52. doi: 10.11648/j.ijimse.20251003.11
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ijimse.20251003.11,
author = {Choe Ryong Bom and Pak Mu Rim and Ro Kang Song and Jo Kwang Bin and Yun Ji Yon},
title = {Mobile Robot Control Using Deep Reinforcement Learning and Autoencoder in Dynamic Environment},
journal = {International Journal of Industrial and Manufacturing Systems Engineering},
volume = {10},
number = {3},
pages = {44-52},
doi = {10.11648/j.ijimse.20251003.11},
url = {https://doi.org/10.11648/j.ijimse.20251003.11},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijimse.20251003.11},
abstract = {In recent years, with the rapid development of artificial intelligence, many innovative changes have been made in the field of intelligent mobile robot development. In the field of control and navigation of mobile robots, learning-based methods have many advantages over traditional ones. The study of mobile robot control methods using deep reinforcement learning is a remarkable area in the development of mobile robots that must operate in dynamic environments. In the previous studies, the proposed robot control algorithms using deep reinforcement learning are mostly based on the given target point and obstacle information, the robot path planning is performed, and the corresponding control is based on the obtained path. The DDPG-based method is a typical example. However, in dynamic environments, DRL based robot path planning requires a state of target point and obstacles information, which leads to a large amount of computation, resulting in extremely long convergence time and even non-convergent cases. In this paper, we propose a new method for mobile robot control in dynamic environment that solves the dimensional problem by extracting the features of the configuration of obstacles using autoencoder and learning the DDPG algorithm based on the obtained features. Simulation results show that the proposed algorithm can effectively solve the mobile robot control problem in dynamic environment.},
year = {2025}
}
TY - JOUR T1 - Mobile Robot Control Using Deep Reinforcement Learning and Autoencoder in Dynamic Environment AU - Choe Ryong Bom AU - Pak Mu Rim AU - Ro Kang Song AU - Jo Kwang Bin AU - Yun Ji Yon Y1 - 2025/12/11 PY - 2025 N1 - https://doi.org/10.11648/j.ijimse.20251003.11 DO - 10.11648/j.ijimse.20251003.11 T2 - International Journal of Industrial and Manufacturing Systems Engineering JF - International Journal of Industrial and Manufacturing Systems Engineering JO - International Journal of Industrial and Manufacturing Systems Engineering SP - 44 EP - 52 PB - Science Publishing Group SN - 2575-3142 UR - https://doi.org/10.11648/j.ijimse.20251003.11 AB - In recent years, with the rapid development of artificial intelligence, many innovative changes have been made in the field of intelligent mobile robot development. In the field of control and navigation of mobile robots, learning-based methods have many advantages over traditional ones. The study of mobile robot control methods using deep reinforcement learning is a remarkable area in the development of mobile robots that must operate in dynamic environments. In the previous studies, the proposed robot control algorithms using deep reinforcement learning are mostly based on the given target point and obstacle information, the robot path planning is performed, and the corresponding control is based on the obtained path. The DDPG-based method is a typical example. However, in dynamic environments, DRL based robot path planning requires a state of target point and obstacles information, which leads to a large amount of computation, resulting in extremely long convergence time and even non-convergent cases. In this paper, we propose a new method for mobile robot control in dynamic environment that solves the dimensional problem by extracting the features of the configuration of obstacles using autoencoder and learning the DDPG algorithm based on the obtained features. Simulation results show that the proposed algorithm can effectively solve the mobile robot control problem in dynamic environment. VL - 10 IS - 3 ER -
Faculty of Mechanical Science and Technology, Kim Chaek University of Technology, Pyongyang, DPR Korea
Faculty of Mechanical Science and Technology, Kim Chaek University of Technology, Pyongyang, DPR Korea
Faculty of Mechanical Science and Technology, Kim Chaek University of Technology, Pyongyang, DPR Korea
Faculty of Mechanical Science and Technology, Kim Chaek University of Technology, Pyongyang, DPR Korea
Faculty of Mechanical Science and Technology, Kim Chaek University of Technology, Pyongyang, DPR Korea
