Multi-objective Mobile Robot Path Planning Based on Improved Genetic Algorithm

Abstract

A multi-objective mobile robot path planning algorithm based on improved genetic algorithm is proposed. The algorithm aims to achieve three kinds of optimization objects for planned paths: length, smoothness and security by introducing the chaotic sequence and heuristic method based on environmental knowledge to initialize population so as to improve the individuals' ergodicity and feasibility in the search space. Meanwhile, according to characteristics of path planning, several genetic operators based on domain-specific knowledge are proposed to improve the algorithm's efficiency. The computer simulation experiments show that the robot can plan a set of optimized smooth paths which can avoid collision from the start to the target point in environment with many obstacles.