A new mobile robot navigation method using fuzzy logic and a modified Q-learning algorithm

Article type: Research Article

Authors: Boubertakh, H.^{; ;} | Tadjine, M. | Glorennec, P.-Y.

Affiliations: LAMEL, University of Jijel, BP. 98, Ouled Aissa, 18000, Jijel, Algeria | LCP, Department of Electrical Engineering, Ecole Nationale Polytechnique, 10 av. Hassen Badi, BP 182, El Harrach, Algiers, Algeria | INSA de Rennes, Department of Informatics, 20 av. des Buttes de Coësmes, 35700 Rennes, France

Note: [] Corresponding author. Hamid Boubertakh. E-mail: [email protected]; [email protected] (M. Tadjine); [email protected] (P.-Y. Glorennec).

Abstract: This paper proposes a new fuzzy logic-based navigation method for a mobile robot moving in an unknown environment. This method endows the robot with the capabilities of obstacles avoidance and goal seeking without being stuck in local minima. A simple Fuzzy controller is constructed based on the human sense and a reinforcement learning algorithm is used to fine tune the fuzzy rule base parameters. The advantages of the proposed method are its simplicity, its easy implementation for industrial applications, and the robot joins its objective despite the environment complexity. Some simulation results of the proposed method and a comparison with some previous works are provided.

Keywords: Fuzzy logic, reinforcement learning, mobile robot navigation, obstacle avoidance

DOI: 10.3233/IFS-2010-0440

Journal: Journal of Intelligent & Fuzzy Systems, vol. 21, no. 1, 2, pp. 113-119, 2010