Automation of synthesized optimal control problem solution for mobile robot by genetic programming

A problem of synthesized control for mobile robot is considered. Initially, a control synthesis problem is solved and a function is found that ensures the stability of the object relative to a point in the state space. The coordinates of the stability points are searched so that when switching form point to point over a given time interval, the robot moves from the initial conditions to the terminal ones without collisions and with the optimal value of the quality criterion. To solve a control synthesis problem a method of complete binary genetic programming is used. To find the coordinates of stability points a particle swarm optimization is applied. Experiments for object with uncertainties in the right parts are given. The sensitivity to different levels of noise for obtaining optimal control by three methods are presented. © Springer Nature Switzerland AG 2020.