Intersection driving track planning method and device and electronic equipment

Abstract

The invention provides an intersection driving track planning method and device and electronic equipment, and the method comprises the steps: taking a current position as an initial node, and determining an extension node through a mixed A * algorithm; if it is determined that a specified curve exists between the extended node and the current target point according to the priority order of the target points, determining an optimal driving path; if no specified curve exists, determining that the distance between the two nodes is smaller than a preset threshold value according to a priority order, and determining the path through backtracking; otherwise, taking the extended node as a new initial node, and repeating the steps to determine the path; and optimizing the optimal driving path by adopting a time elastic band algorithm to obtain an intersection driving track. According to the method, the optimal driving path of the vehicle at the intersection can be automatically searched by adopting the mixed A * algorithm, and the searched optimal driving path is optimized by adopting the time elastic band algorithm, so that the intersection driving track on which the vehicle can actually run is obtained; therefore, the planning efficiency and accuracy of the intersection driving track can be improved.

Description

technical field [0001] The present invention relates to the technical field of automatic driving, in particular to a planning method, device and electronic equipment for intersection driving trajectories. Background technique [0002] In related technologies, the trajectory planning method for autonomous vehicles at intersections is mainly to artificially fit virtual lane lines at intersections to construct a road network, thereby generating a virtual road centerline as a virtual reference line for planning; specifically, usually first Path planning is performed on the virtual reference line, followed by speed planning, and finally the path and speed are combined to obtain the final trajectory. In this method, in order to cover as many driving scenarios as possible, it is necessary to artificially draw enough possible virtual lane lines at the intersection to connect different entry points and exit points of the intersection. When there are many lanes at the intersection and...

AI Technical Summary

Problems solved by technology

In this method, in order to cover as many driving scenarios as possible, it is necessary to artificially draw enough possible virtual lane lines at the intersection to connect different entry points and exit points of the intersection. When there are many lanes at the intersection and the traffic conditions are complex When , constructing the road network will consume a lot of time and energy, and it is very error-prone, resulting in low efficiency and poor accuracy of intersection trajectory planning

Images