Intelligent vehicle path planning method based on potential energy field probability graph in off-road environment

Abstract

The invention discloses an intelligent vehicle path planning method based on a potential energy field probability graph in an off-road environment. The method comprises the following steps: S1, establishing a multi-level environment situation field model for evaluating off-road environment risks by adopting an artificial potential energy field method; s2, establishing a cross-country environment space topological graph, and generating a multi-dimensional node connection evaluation model; s3, starting from the current node, searching expansion nodes communicated with the current node around thecurrent node, and evaluating the passing cost of each expansion node; s4, starting from the starting point of the path, searching new expansion nodes, and evaluating the passing cost of each new expansion node until the new expansion nodes are expanded to a target end point; and S5, generating a vehicle motion track. According to the method, the potential energy value of the environment situationfield can be output according to the multi-dimensional cross-country environment information around the vehicle, the cross-country environment space topological graph is established by adopting a random sampling method, the optimized path is generated by evaluating the cross-country environment passage risk between the nodes in the topological graph, and the feasible, safe and efficient intelligent vehicle driving target is achieved.

Description

technical field [0001] The invention relates to the technical field of automatic driving, in particular to an intelligent vehicle path planning method based on a potential energy field probability map in an off-road environment. Background technique [0002] Smart vehicles can complete tasks such as intelligence acquisition, reconnaissance and surveillance, logistics transportation, and communication transfer in complex off-road environments, and play a vital role in emergency rescue operations such as sudden epidemics, natural disasters, and accident rescue. Smart car path planning in off-road environment determines whether the smart car can complete various driving behaviors safely, efficiently and smoothly during driving, and reach the target destination smoothly. It is a key technology in the field of smart car automatic driving. [0003] In recent years, intelligent vehicle autonomous driving path planning technology has developed rapidly, which can be divided into five...

AI Technical Summary

Problems solved by technology

[0006] The present invention has the following advantages due to the adoption of the above technical solutions: the path planning method under the off-road environment provided by the present invention first adopts the potential energy field method to respectively establish a hierarchical off-road environment situation field quantification for obstacles, threats and roads in the off-road environment Model, and using the environmental situation field quantitative model to establish a comprehensive feasibility, safety, and high-efficiency multi-level traffic cost assessment method between environmental nodes; for the vehicle traffic risk assessment problem under complex off-road environment conditions, using offline learning In this way, a multi-dimensional node connection evaluation model between nodes is established to evaluate the risk of vehicle traffic in complex off-road environments, and a path node expansion and optimization method with traffic cost as the evaluation index is proposed, which can be based on vehicle performance and task It is required to adjust the weight coefficient matrix to select the traffic path that is suitable for the performance of the vehicle; finally, the dynamic curvature smoothing method is used to generate the vehicle trajectory

Images