基于动态虚拟障碍物的智能车辆局部路径规划方法

针对传统人工势场法在智能车辆局部路径规划中未充分考虑车辆动力学和运动学约束的不足,提出一种基于动态虚拟障碍物的局部路径规划方法.首先根据环境、车辆运行状态和道路交通规则分析车辆行驶安全性并获得虚拟车道线的解析表达,再进行车辆驾驶行为决策并生成受约束的动态虚拟障碍物,最后采用考虑动力学和运动学约束的改进人工势场法进行局部路径规划.仿真实验表明,该方法在保证动力学和运动学约束的前提下,能够在不同初始速度、相对速度和相对距离工况下获得较好的规划性能.

Dynamic Virtual Obstacle Based Local Path Planning for Intelligent Vehicle

Traditional artificial potential field (APF) method can hardly be applied directly to intelligent vehicle local path planning, as it does not take into account the dynamics and kinematics constraints. A dynamic virtual obstacle based local path planning method was presented to solve this problem. Firstly, environment information, vehicle operation status and traffic rules were used to analyze driving safety, and the analytical expression of the virtual lane was deduced. Secondly, driving operation decision was made and constrained dynamic virtual obstacles were generated according to the decision. Finally, the local path was planned on the basis of an improved APF with dynamics and kinematics constraints. Simulation results show that the proposed method can achieve better planning performance at various initial speeds, relative speeds and relative distance under the condition of dynamics and kinematics constraints.