基于改进人工势场的智能车动态避障算法

Dynamic obstacle avoidance algorithm of intelligent vehicles based on improved artificial potential field

针对传统人工势场法在动态环境中易与障碍物发生碰撞的问题,采用了一种适用于动态环境的改进型人工势场法。通过进行局部极小值检测并增设虚拟子目标点,解决了传统人工势场法存在的局部最优问题;通过引入智能车和目标点的相对距离因子对障碍物的斥力势场进行调控,使目标点处的合力势场为全局最小值,减少了障碍物在目标点附近对智能车的影响,使智能车顺利到达目标点;通过在斥力势场函数中引入障碍物相对速度势场和道路边界势场,解决了动态障碍物条件下人工势场法经常面临的碰撞问题。仿真实验结果显示,改进后的人工势场算法可以在动态障碍物环境中规划出一条安全可靠的行驶路径。

In order to solve the vehicle collision with obstacles in dynamic environment by traditional artificial potential field method,an improved artificial potential field(APF)method suitable for dynamic environment is investigated.The local minimum value is detected and the virtual sub-target point is added to solve the local optimum problem of the traditional artificial potential field method.By introducing the relative distance factor between the intelligent vehicle and the target point,the repulsion potential field of the obstacle is regulated,so that the resultant potential field at the target point is the global minimum value,and the influence of the obstacle on the intelligent vehicle near the target point is reduced.The potential field of relative velocity of obstacles and the potential field of road boundary are introduced to the repulsion potential field function.This solves the collision problem often faced by the artificial potential field method under dynamic obstacle conditions.The simulation results show that the improved artificial potential field algorithm can plan a safe and reliable driving path in the dynamic obstacle environment.