基于蚁群算法的智能汽车轨迹控制方法研究

Research on intelligent vehicle track control method based on ant colony algorithm

针对基础蚁群算法易陷入局部最优且收敛速度较差等问题,提出了一种基于自适应策略和蚁群算法的智能汽车轨迹控制与路径规划算法。该算法在初始信息素浓度的分配中,使用自适应函数完成信息素浓度的差异化分配,从而减少了错误浓度信息对路线选择的影响。同时,设计了新的概率转移函数,使不同算法场景拥有不同的概率权重,显著提升了算法的收敛速度。为防止算法陷入局部最优,基于自适应信息熵制定了全局信息素更新规则,令算法在路径规划过程中可兼具性能及效率。仿真测试结果表明,所提算法的路径规划质量在对比算法中为最优,且迭代次数较少,运行时间也仅为5.1 s,证明该算法具有良好的综合性能。

Aiming at the problems of local optimization and poor convergence speed of basic ant colony algorithm,this paper proposes an intelligent vehicle trajectory control and path planning algorithm based on adaptive strategy and ant colony algorithm.In the allocation of initial pheromone concentration,the algorithm uses an adaptive function to complete the differential allocation of pheromone concentration,so as to reduce the impact of wrong concentration information on route selection.A new probability transfer function is designed,so that different scenarios have different probability weights,and the convergence speed of the algorithm is significantly improved.In order to prevent the algorithm from falling into local optimization,a global pheromone update rule is formulated based on adaptive information entropy,which makes the algorithm have both performance and efficiency in the process of path planning.In the simulation test,the path planning quality of the algorithm in this paper is the best in the comparison algorithm,the number of iterations is small,and the running time is only 5.1 s,which proves that the improved algorithm has good comprehensive performance.