Path Planning of Mobile Robot Based on Improved Differential Evolution Algorithm

With the rapid development of intelligent algorithms, it has become an inevitable trend to use intelligent algorithm with high intelligence and strong adaptability for robot path planning. Differential evolution algorithm (DE) is a typical intelligent algorithm applied in the robot path planning, yet there still exist some disadvantages, such as local optimum and computational redundancy. Aiming at these defects, this paper proposed an improved differential evolution algorithm (IDE) for robot path planning problem. In the proposed algorithm, chaos initialization population method is used to improve the ergodicity of search, and a judgment mechanism is introduced to ensure that the paths are available. Furthermore, the control parameters are updated according to a modified parameter adaptation strategy in each generation. Finally, the simulation results show that the IDE has better performance in convergence speed, optimization precision and stability compared with DE. Moreover, the experimental results of global path planning based on the robot operating system (ROS) further verify the feasibility and validity of the proposed algorithm.