五次多项式优化的平行泊车路径规划

针对目前自动泊车路径规划普遍存在的曲率突变问题，提出了一种五次多项式优化的平行泊车路径规划方法。五次多项式曲线由约束条件建立的方程组求解得出，并对路径的曲率突变处进行过渡优化。为简化计算，引入“虚圆半径”的概念，以“虚圆半径”作为最小转弯半径，并按照“圆弧-直线-圆弧”平行泊车路径规划的方法进行求解，由此得出优化的平行泊车路径。仿真结果表明，五次多项式优化的平行泊车路径规划方法能够规划出曲率连续、满足避障约束和车辆运动学约束的优化路径，提高了路径跟踪的效果，保证车辆安全完成泊车。

Optimized Parallel Parking Path Planning Based on Quintic Polynomial

In order to solve the common problem of curvature mutation in automatic parking path planning, an optimized path planning method of parallel parking based on quintic polynomial is proposed. The quintic polynomial curve, obtained by solving equations set which is established according to the constraint conditions, can be used to optimize the path of curvature mutation. In order to simplify the calculation, the concept of “virtual circle radius” is introduced as the minimum turning radius, and by the arc-straight-arc parallel parking path planning method, the optimized parallel parking path can be obtained. The simulation results show that this path planning method can plan an optimal path with continuous curvature, satisfying obstacle avoidance constraint and vehicle kinematics constraint, enhances the tracking effect, and ensures the safety of the vehicle parking.