RESEARCH ON SELF-PROPELLED ROBOTS CONTROL APPLICATION FOR INTELLIGENT NAVIGATION BASED ON Q-LEARNING ALGORITHM

Trần Thị Hường

doi:10.34238/tnu-jst.5745

RESEARCH ON SELF-PROPELLED ROBOTS CONTROL APPLICATION FOR INTELLIGENT NAVIGATION BASED ON Q-LEARNING ALGORITHM

About this article

Received: 22/03/22 Revised: 12/05/22 Published: 19/05/22

Authors

Tran Thi Huong , University of Economics - Technology for Industries

Abstract

This paper presents a study on controlling automotive robots applied in industry, civil, etc. for intelligent navigation in unknown environment on the basis of Q-Learning algorithm. The programming tool is the operating system for the robot ROS (Robot Operating System) and performs automatic intelligent navigation for the robot with the process of locating the robot in a flat environment and mapping (called SLAM-Simultaneous Localization and Mapping). Research results using ROS programming tool, in Gazebo environment. The information is updated from the map, operating environment, control position of the robot, and obstacles to calculate the trajectory for the robot in the automatic navigation system. The goal is to safely avoid the obstacles without encountering any obstacles along the way.

Keywords

Automotive robot; ROS; SLAM; Gazebo; Intelligent navigation

Full Text:

PDF (Tiếng Việt)

References

[1] Q. C. Hoang, H. V. Dao, A. V. Nguyen, and B. C. Le, Electric drive systems in Robots. People's Army Publishing House, (in Vietnamese), Hanoi, Vietnam, 2020.

[2] D. P. Nguyen, Advanced Control Theory. Science and Engineering Publishing House, (in Vietnamese), Hanoi, Vietnam, 2018.

[3] H. S. Le, C. D. Le, and V. H. Nguyen, Industrial Robots Syllabus. Ho Chi Minh City National University Publishing House, (in Vietnamese), Ho Chi Minh City, Vietnam, 2017.

[4] T. T. Nguyen, Basic Deep Learning, 2nd, The Legrand Orange Book Template by Mathias Legrand, Publishing by Vietnamme, (in Vietnamese), Hanoi, Vietnam, 2020.

[5] L. Joseph and J. Cacace, Mastering ROS for Robotics Programming. Second Edition: Design, build, and simulate complex robots using the Robot Operating System, Published by Packt Publishing Ltd. N0. 35 Livery Street Birmingham B3 2PB, UK, 2018.

[6] S. P. Thale et al., “ROS based SLAM implementation for Autonomous navigation using Turtlebot,” ITM Web of Conferences 32, 01011, 2020.

[7] S. Ohnishi, E. Uchibe, Y. Yamaguchi, K. Nakanishi, Y. Yasui, and S. Ishii, “Constrained Deep Q-Learning Gradually Approaching Ordinary Q-Learning,” Frontiers in Neurorobotics Journal, vol. 13, pp. 7-12, 2019.

[8] R. K. e. a. Megalingam, “ROS based autonomous indoor navigation simulation using SLAM algorithm,” Int. J. Pure Appl., vol. 118, no. 7, pp. 199-205, March 2018.

[9] H. X. Dong, C. Y. Weng, C. Q. Guo, H. Y. Yu, and I. M. Chen, “Real-time avoidance strategy of dynamic obstacles via half model-free detection and tracking with 2D Lidar for mobile robots,” IEEE/ASME Transactions on Mechatronics, vol. 26, no. 4, pp. 2215-2225, Aug 2021.

[10] D. Kozlov, “Comparison of Reinforcement Learning Algorithms for Motion Control of an Autonomous Robot in Gazebo Simulator,” International Conference on Information Technology and Nanotechnology, IEEE Explore, vol .9, pp. 1-5, 2021, doi: 10.1109/ITNT52450.2021.9649145.

DOI: https://doi.org/10.34238/tnu-jst.5745

Refbacks

There are currently no refbacks.



Remember me