Multi-thread evolutionary programming and its application to truck-and-trailer backer-upper control

This paper presents a multi-thread evolutionary programming (MEP) technique that is composed of global, local, and minimal search units. An appropriat e starch routine is called depending on the current situation and the indiv iduals are updated by using the selected routine. In each search routine, t he individuals are updated with a normalized relative fitness function to i mprove the robustness of the algorithm. The proposed method is applied to t he problem of backing up a truck-and-trailer system to a loading dock. A fu zzy logic controller is designed for a truck-and-trailer backer-upper syste m and the MEP algorithm is used to optimize the representative parameters o f the fuzzy logic controller. The simulation results show that the proposed controller performs well even under a large variety of initial positions.