Affiliations: Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing, China
Correspondence:
[*]
Corresponding author. Min Xia, Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing, China. E-mail: [email protected].
Abstract: Robot path planning is integral to many robotic applications. In this work, three optimization objectives are presented: path length, degree of path smoothness, and degree of security. Due to the lack of local search ability, the optimal solution set is difficult to be obtained with the traditional method especially when the search space is very irregular. And the simple local search algorithm is often trapped into local optimization. A new method with local search is introduced to improve the SPEA2 in this work. The proposed method sets up an external population dedicated to local search, which can increase the local search ability of the method while retaining good global searching ability. In addition, the new crossover operator and the individual update strategy are used for proposed method. The simulation results shows that the proposed method is better than that of SPEA2, NSGA-2 and PESA. It was found that the model proposed in this work is practical for robot path planning.
