A Guidance Strategy for Parking Space of Autonomous Valet Parking with Cooperative Vehicle Infrastructure System

Abstract

<div class="section abstract"><div class="htmlview paragraph">Lots of invalid volume of traffic occurs as the vehicle repeatedly seeking the valid berth location, due to the existence of information islands, which reduces traffic efficiency, increases traffic congestion and the emission of pollutants. Aiming at eliminating the existence of information islands, this paper proposed a guidance strategy for parking space of autonomous valet parking, as taking merits of cooperative vehicle infrastructure system. The guidance strategy consists of an optimal guidance model and an adaptive ant-colony algorithm. Firstly, the optimal guidance model takes the minimum total parking cost as the objective function and the capacity of parking space as the constraints. Both the objective costs of parking and the subjective cost of customer are taken into accounts in the objective function. Secondly, comparing with traditional method, the adaptive ant-colony algorithm taking two improvements, in order to accelerate the convergence of the algorithm and avoid falling into the local optimal solution in early time. The first improvement preserves the optimal solution for each iteration, and the second improvement changes pheromone evaporation coefficient according to certain rules. The illustrative example shows that the method presented in this paper can reduce the phenomenon of repeated berth seeking and the cost of parking system.</div></div>