智能网联下无人驾驶汽车配送路径优化方法

Route Optimization Methodology for Unmanned Vehicle Distribution in Intelligent Network

为充分利用城市道路资源,提高物流配送效率,以未来无人车在物流配送领域的全新应用为背景,从无人车环境感知与协同决策的角度,提出智能网联环境下无人车配送路径优化方法.研究以总成本最小为优化目标,构建同时取送货、带软时间窗约束的无人车配送路径优化模型.根据优化模型的特点与求解需求,设计多种群遗传算法进行求解.分别针对小规模与大规模算例进行测试,并将结果与标准遗传算法(SGA)结果进行比较.结果表明,多种群遗传算法(MPGA)在对两种规模算例进行求解时具备较好寻优效果,其稳定性、寻优性以及收敛性均优于SGA.该研究可为未来无人车在物流配送领域的运营管理提供借鉴.

From the perspective of unmanned vehicle environment perception and collaborative decision-making,route optimization methodology for unmanned vehicle distribution is proposed to make use of urban road resources and improve the efficiency of logistics distribution with new application of unmanned vehicles in the field of logistics.The unmanned vehicle distribution route optimization model with simultaneous delivery and soft time window constraints is constructed for the objective of minimum total cost.According to the characteristics of model and solution requirements,a multi-group genetic algorithm is designed to solve the problem.The model is tested for small-scale and large-scale,and the results are compared with standard genetic algorithm(SGA)results.The results show that the multi-population genetic algorithm(MPGA)has better optimization results,and its stability,optimization and convergence are better than SGA.This research can provide reference for operation and management of unmanned vehicles in the field of logistics.