Global path planning of intelligent vehicle based on improved bidirectional parallel A* algorithm

Abstract:
At present, the global path planning of intelligent vehicle has the problems of long search time, many redundant points, low path smoothness and low applicability of intelligent vehicle. To solve these disadvantages, this paper proposes an improved bidirectional parallel A* algorithm as the global path planning algorithm. The traditional A* algorithm is improved by using bidirectional parallel search of start and end points, setting safe distance and redefining heuristic function. Aiming at the problem that there are many redundant points in the path planned by the traditional A* algorithm, the measures of selecting key turning points and using cubic B-spline curve for path smoothing are proposed. The final simulation results show that the planned global path has good effect and can meet the requirements of intelligent vehicle follow-up control. The improved bidirectional parallel A* algorithm has the characteristics of fast search speed, less redundant points and high smoothness of the planned path.