Title: Research on multi-objective path planning of a robot based on artificial potential field method
Authors: Hu Yunqiang; Ke Wende; Chang Lin; Leng Xiaokun
Addresses: School of Innovation and Entrepreneurship, Southern University of Science and Technology, Shenzhen 518055, China; Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen 518055, China ' Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen 518055, China; Department of Computer Science, Guangdong University of Petrochemical Technology, Maoming 525000, China ' School of Computer Science, Harbin Institute of Technology, Harbin 150001, China ' School of Computer Science, Harbin Institute of Technology, Harbin 150001, China
Abstract: Aiming at the shortcomings of traditional artificial potential field method, which easily falls into zero potential field in the case of complex obstacles and can't guarantee the optimal path, a multi-objective path planning based on artificial potential field method is proposed. The method takes the path length and path security as the optimisation targets, and the obstacle repulsion coefficient as the decision variable. The objective function is calculated by establishing the artificial potential field performance model, and the NSGA-II algorithm is used for multi-objective optimisation to obtain the optimal path. The flexibility of decision variables prevents the path from falling into zero potential field points, and multi-objective optimisation ensures path length and security optimisation. The simulation results prove the feasibility and superiority of the method.
Keywords: robot path planning; multi-objective optimisation; artificial potential field.
DOI: 10.1504/IJWMC.2018.097194
International Journal of Wireless and Mobile Computing, 2018 Vol.15 No.4, pp.335 - 341
Received: 18 Aug 2018
Accepted: 18 Oct 2018
Published online: 02 Jan 2019 *