粒子群优化算法在智能车辆轨迹跟踪的应用
Application of Particle Swarm Optimization Algorithm in Intelligent Vehicle Trajectory Tracking
丁志成 1王甜甜2
作者信息
- 1. 郑州工业应用技术学院机电工程学院,河南 郑州 451100
- 2. 郑州西亚斯学院电子工程学院,河南 郑州 451150
- 折叠
摘要
针对智能车辆的局部规划与路径跟踪的协同控制问题,提出了一种基于改进粒子群优化(IPSO)的模型预测控制(MPC)方法.首先将模型预测控制与人工势场(APF)相结合,将时变安全约束作为排斥力的范围和非对称的车道势场函数,通过将时变安全约束视为排斥力的范围和非对称车道势场函数来获得无碰撞路径,在此基础上,将APF与IPSO-MPC相结合,采用伪速度规划算法来处理交通灯和运动障碍的约束,从而有效地解决了路径优化问题.仿真结果验证了该算法的有效性,与一般算法相比具有明显的优越性.
Abstract
Aiming at the cooperative control problem of local planning and path tracking of intelligent vehicles,a model predic-tive control(MPC)method based on Improved Particle Swarm Optimization(IPSO)is proposed.Firstly,the model predictive control is combined with the artificial potential field(APF),and the time-varying safety constraint is regarded as the range of repulsion force and the asymmetric Lane potential field function.The collision free path is obtained by treating the time-varying safety constraint as the range of repulsion force and the asymmetric Lane potential field function.On this basis,APF is combined with IPSO-MPC.The pseudo speed programming algorithm is used to deal with the constraints of traffic lights and moving ob-stacles,so as to effectively solve the path optimization problem.Simulation results verify the effectiveness of the algorithm,which has obvious advantages compared with general algorithms.
关键词
粒子群算法/车辆轨迹跟踪/局部规划/人工势场/模型预测控制Key words
Particle Swarm Optimization/Vehicle Track Tracking/Local Planning/Artificial Potential Field/Model Predictive Control引用本文复制引用
基金项目
河南省高等学校科研一般项目(2020)(2020YB036)
出版年
2024
NETL
NSTL
维普
万方数据