A Multi-objective Optimization Model for Determining the Optimal Standard Feasible Neighborhood of Intelligent Vehicles

Lei Huang, Ying Xu, Hailiang Zhao

Abstract: Due to the complex conditions on the roads, intelligent vehicles need to face infinite environments. Based on the neighborhood control theory, the infinite world can be reduced to a limited and irregular feasible area. By constructing a finite number of feasible neighborhoods within the feasible region, an optimal standard feasible neighborhood can be determined for intelligent vehicle. This paper proposes a standard feasible neighborhood for the intelligent vehicle based on the ladder-sector. Then a new multi-objective optimization model for determining the optimal standard feasible neighborhood has been proposed. A partition method has been designed by transforming the problem from the infinite feasible domain into a series of feasible neighborhoods. Finally, simulations have been carried out on some representative road conditions. Simulation results demonstrate the effectiveness of the proposed multi-objective optimization model.