Differential evolution for optimizing motion planning of mobile robot

Abstract

The demand for faster, more precise and more sophisticated solutions in industrial robotics is growing more and more. People keep seeking for a better solution for robotic problems in general and mobile robots in particularly to meet this demand. In this paper, we propose a new evolutionary approach called Differential Evolution (DE) that can be employed to optimize the path planning task for mobile robots. The path not only needs to be optimized but also needs to be easy to traverse for non-holonomicity. Therefore, the path smoothening B-spline technique is integrated with the DE approach to provide traversable path for mobile robots. Our system has been implemented and evaluated on an Aria mobile robot in both simulated and real environments.