Dynamic trajectory planning method for unmanned vehicle based on local optimum

Abstract

The invention belongs to the technical field of a path planning for unmanned vehicles, and especially relates to a dynamic trajectory planning method for an unmanned vehicle based on local optimum. The method is characterized by, according to different positions and corresponding different operating conditions of obstacle vehicles on the road, selecting an optimal reference trajectory and carryingout dynamic trajectory planning; analyzing unmanned vehicle lane change intention generation and lane change executable conditions, and according to the prediction of the position and speed of surrounding obstacle vehicles, carrying out fitting to obtain a locally optimal lane change trajectory at the initial moment when obstacle avoidance lane change is decided, and serving the optimal trajectory as a local reference trajectory; and generating a trajectory cluster that can be driven by the unmanned vehicles and combining designed velocity distance and cost functions with a loss function, andselecting an optimal trajectory from the trajectory cluster through nonlinear model predictive control. The method can realize obstacle avoidance, lane change and overtaking in various complex conditions, and also takes into account the comfort of passengers in the unmanned vehicles and road driving efficiency and the like.

Description

technical field [0001] The invention belongs to the technical field of path planning for unmanned vehicles, and in particular relates to a dynamic trajectory planning method for unmanned vehicles based on local optimality. Background technique [0002] With the progress and development of the times, unmanned driving technology has fundamentally brought about social changes. Unmanned driving can essentially change people's lifestyles and travel methods, and is very intelligent. Unmanned vehicles are an important part of the intelligent transportation system. Since unmanned vehicles integrate many fields such as environmental perception, positioning, decision-making, and tracking control, they have the advantages of sensitive response, safe and reliable driving, etc., which can effectively reduce the occurrence of traffic accidents. rate and improve the driving efficiency of vehicles on the road. At present, many high-end technology companies at home and abroad are committed ...

AI Technical Summary

Problems solved by technology

[0004] In the existing path planning algorithms for unmanned vehicles, the trajectory planning research is generally based on the given obstacle vehicle conditions, and the comfort of passengers and the road driving of unmanned vehicles when avoiding obstacles and changing lanes are rarely considered. efficiency

Images