Automatic driving vehicle trajectory planning method and system

Abstract

The invention belongs to the field of vehicle trajectory planning, and provides an automatic driving vehicle trajectory planning method and system. The method comprises the following steps of acquiring a vehicle driving reference line and an obstacle map, performing longitudinal sampling and transverse sampling on the final position to obtain a position sampling set and a speed sampling set, traversing sampling points from the position sampling set, and estimating the trajectory length in a heuristic mode, traversing the sampling speed from the speed sampling set, estimating the target time, and calculating a trajectory equation, judging the integrity of the trajectory according to the time length of the trajectory, calculating the trajectory cost of the complete trajectory, storing the trajectory cost into an ordered queue, and after the speed sampling traversal is finished, sequentially taking out the trajectory with the minimum cost from the ordered queue and carrying out collision detection until the ordered queue is empty, and outputting a planned autonomous vehicle trajectory based on the collision detection and the trajectory risk factor.

Description

technical field [0001] The invention belongs to the field of vehicle trajectory planning, and in particular relates to a method and system for autonomous vehicle trajectory planning. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] With the rapid development of e-commerce and rising labor costs, the "last mile" problem of logistics distribution has become more and more prominent: the last distance of transportation logistics accounts for one-third of the total transportation cost, especially for large-scale This is an even greater challenge in sparsely populated rural areas. Therefore, the logistics industry has put forward an increasing demand for low-speed unmanned vehicles capable of passing through complex road environments in cities and rural areas. Among them, trajectory planning is the core component of unmanned driving technology,...

AI Technical Summary

Problems solved by technology

However, the algorithm is still based on the Frenet coordinate system for planning, which is not suitable for low-speed planning

[0009] To sum up, since low-speed logistics vehicles operate in environments with no clear road range, changing environments, and many obstacles in many cases, such as parks and campuses, it is necessary to use the flexibility within the allowable range as much as possible. However, the inventors found that most of the current trajectory planning methods for self-driving vehicles are for long-distance planning, and there is basically no need to consider whether it can be actually executed; while the flexible obstacle avoidance method using robots will cause Vehicle instability and more likely to cause traffic accidents

Images