多项式曲线优化的垂直泊车路径规划与跟踪

Polynomial curve-optimized vertical parking path planning and tracking

为提高复杂环境下自动垂直泊车的安全性和成功率,提出一种基于多项式曲线优化的垂直泊车路径规划方法和跟踪控制策略.首先,基于直线-圆弧路径下逆向泊车的方法,计算垂直泊车可行起始点范围.其次,综合考虑车辆位置结构和道路边界约束,以多项式为基函数、泊车终点姿态角最小为目标,建立多约束非线性规划路径函数模型,利用粒子群算法求解垂直泊车路径.最后,结合模糊神经网络控制方法,设计路径跟踪控制器.构建Simulink/CarSim仿真模型,对所提路径规划方法和跟踪策略进行仿真,结果验证了所提泊车路径规划和跟踪控制策略的可行性和有效性.

A novel vertical parking path planning and tracking control methodology based on polynomial curve optimization is proposed in this paper.First,the available range of starting position for vertical parking is computed by means of straight-arc path with reverse parking.Secondly,taking the size constraints of vehicle and road into consideration,a multi-constraint nonlinear programming path function model is established with a polynomial basis function and the goal of minimum parking end attitude angle suggested.Consequently,the vertical parking path is figured out using particle swarm optimization algorithm.As a result,with combination of the fuzzy neural network control method,the path tracking controller based on Simulink/CarSim platform is designed and the feasibility and effectiveness of the proposed parking path planning and tracking control is verified by the simulation results.