基于SSA-SVM车辆换道决策模型设计

Design of vehicle lane change decision model based on SSA-SVM

为解决传统支持向量机算法(Support Vector Machine,SVM)应用于智能驾驶车辆换道决策阶段时出现的决策分类不精确问题,提出一种结合智能优化算法的支持向量机模型分类算法,将智能优化算法中的麻雀搜索算法(Sparrow Search Algorithm, SSA)应用到支持向量机中,可以进行惩罚参数和核函数自适应调整,避免人工经验试凑的不足,加速算法收敛。采用MATLAB软件对车辆换道决策模型建模,应用改进的SSA-SVM算法进行决策分类。仿真结果表明:相对于传统的SVM算法,该算法有效加速迭代收敛,大幅提高算法分类准确度。

In order to solve the problem of inaccurate classification of traditional Support Vector Machine(SVM)algorithms when applied to the decision making stage of lane changing of intelligent driving vehicles,a support vector machine model classification algorithm combined with intelligent optimization algorithm is proposed,which applies the Sparrow Search Algorithm(SSA)of intelligent optimization algorithm to the support vector machine.The Sparrow Search Algorithm(SSA)of the Intelligent Optimization Algorithm is applied to the support vector machine,which can perform adaptive adjustment of penalty parameters and kernel functions to avoid the shortage of manual empirical trial and error and accelerate the convergence of the algorithm.The MATLAB software is used to model the vehicle lane change decision model,and the improved SSA-SVM algorithm is applied to classify the decision.The simulation results show that the algorithm is effective in accelerating the convergence of the iterations compared with the traditional SVM algorithm and significantly improves the classification accuracy of the algorithm.