Intelligent vehicle obstacle avoidance lane changing trajectory planning method and system

Abstract

The invention discloses an intelligent vehicle obstacle-avoiding lane-changing trajectory planning method and system, and the method comprises the steps: generating a feasible trajectory cluster based on an operation stability limit starting return point and a polynomial curve according to a road environment, obstacle information and a current vehicle speed, carrying out the pre-collision detection of a lane-changing trajectory in the feasible trajectory cluster, and carrying out the pre-collision detection of the lane-changing trajectory in the feasible trajectory cluster; screening and removing tracks which do not meet the pre-collision detection condition to obtain a collision-free track cluster; establishing a cost function about three evaluation indexes of comfort, obstacle avoidance efficiency and sideslip on the basis of the collision-free trajectory cluster; and the weights of the three evaluation indexes are determined by adopting fuzzy reasoning, and the optimal obstacle-avoiding lane-changing return point is searched by solving a multi-objective optimization problem, namely, the final obstacle-avoiding lane-changing track is planned. Meanwhile, the invention further provides an intelligent vehicle obstacle-avoiding lane-changing trajectory planning system, performance indexes such as comfort and obstacle-avoiding efficiency of the trajectory can be maximized while safety, real-time performance and curvature continuity are considered, and the riding experience of passengers is effectively improved.

Description

technical field [0001] The invention belongs to the technical field of intelligent driving vehicle planning, and in particular relates to a trajectory planning method for an intelligent vehicle to avoid obstacles and change lanes. Background technique [0002] At present, the number of motor vehicles in my country is increasing year by year, and the problems of traffic safety and road congestion are becoming more and more prominent. Studies have shown that human factors such as driver inattention or lack of driving experience are the main causes of traffic accidents. Therefore, intelligent driving vehicles are developing and progressing rapidly. It can bear more burden and pressure of human drivers, thereby improving road safety. The key technologies include perception, positioning, decision-making, planning and control. [0003] At present, the active obstacle avoidance strategies of intelligent vehicles are mainly divided into two types: braking obstacle avoidance and ste...

AI Technical Summary

Problems solved by technology

Among them, the sampling-based method is generally real-time and the generated curve may have sudden changes in curvature; although the curve interpolation method has good real-time performance and continuous curvature, it has poor flexibility; and the numerical optimization method needs to deal with multi-constrained search problems, and the calculation cost is very high. high

Various planning methods have their own characteristics, and a single method cannot achieve optimal planning.

Images