Unmanned vehicle's optimal control based on the selection function and network operators
Anna N. Daryina, Igor V. Prokopiev · 2020
The paper presents a method for optimal control of an unmanned vehicle taking into account real-time constraints; environmental parameters are not known in advance. At the first step, an unmanned vehicle is identified at the training ground, then the optimal trajectory is selected. To construct the control function and the selection function, evolutionary methods of symbolic regression are used. The synthesis is carried out by a network operator, which was modeled in gazebo. Also, the way of using the proposed method on the example of the mobile robot's movement along a track with dynamic and static restrictions is presented.