Abstract
In this paper we propose a new application sensor-based navigation method for navigation of wheeled mobile robot, based on neural dynamic programming (NDP). We discuss a sensor-based approach to path design and control of wheeled mobile robot (WMR) in an unknown 2-D environment with static obstacles. A strategy of navigation is developed including two main behaviors: a reaching the middle of a collision-free space behavior, and a goal-seeking. The NDP navigator which is the main theme of this paper, can fuse behaviors so that the mobile robot can go for the goal position without colliding with obstacles for the concave and convex obstacles. This solution is based on the reinforcement learning (RL) method of actor-critic architecture for continuous-time, and does not require pre-learning and working on-line. Computer simulations have been conducted to illustrate the performance of the proposed solution by a series of experiments.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ali, M.A., Mailah, M.: A simulation and experimental study on wheeled mobile robot path control in road roundabout environment. Int. J. Adv. Rob. Syst. 16(2), 1729881419834778 (2019)
Arkin, R.C.: Behaviour-Based Robotics. The MIT Press, Cambridge (1998)
Barto, A.G., Sutton, R.S., Anderson, C.W.: Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Trans. Syst. Man Cybern. SMC-13(5), 834â846 (1983)
Doya, K.: Reinforcement learning in continuous time and space. Neural Comput. 12(1), 219â245 (2000)
Fiorato, N., Yasutaka, F., Roberto, O.: A LSTM neural network applied to mobile robots path planning. In: IEEE 16th International Conference on Industrial Informatics (INDIN), pp. 349â354 IEEE (2018)
Giergiel, J., Ć»ylski, W.: Description of motion of a mobile robot by Maggieâs equations. J. Theor. App. Mech. 43, 511â521 (2005)
Hendzel, Z.: Collision free path planning and control of wheeled mobile robot using Kohonen selforganising map. Bull. Polish Acad. Sci. Techn. Sci. 53(1), 39â47 (2005)
Levis, F.L., Liu, K., Yesildirek, A.: Neural net robot controller with guaranteed tracking performance. IEEE Trans. Neural Netw. 6(3), 703â715 (1995)
Chang, L., Shan, L., Jiang, C., Dai, Y.: Reinforcement based mobile robot path planning with improved dynamic window approach in unknown environment. Auton. Robot. 45(1), 51â76 (2020). https://doi.org/10.1007/s10514-020-09947-4
Ramanathan, K.C., Mohan, M., Dhanraj, J.A.: Backward motion planning and control of multiple mobile robots moving in tightly coupled formations. Appl. Comput. Sci. 17(3), 60â72 (2021)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, second edn. Cambridge MIT Press, Cambridge (2018)
Szuster, M., Hendzel, Z.: Intelligent Optimal Adaptive Control for Mechatronic Systems. Springer, Heidelberg (2018). https://doi.org/10.1007/978-3-319-68826-8
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hendzel, Z., KoĆodziej, M. (2022). Neural Dynamic Programming with Application to Wheeled Mobile Robot. In: Szewczyk, R., ZieliĆski, C., KaliczyĆska, M. (eds) Automation 2022: New Solutions and Technologies for Automation, Robotics and Measurement Techniques. AUTOMATION 2022. Advances in Intelligent Systems and Computing, vol 1427. Springer, Cham. https://doi.org/10.1007/978-3-031-03502-9_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-03502-9_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-03501-2
Online ISBN: 978-3-031-03502-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)