Multi-objective optimization method for vehicle traffic decision-making at urban intersections based on conflict resolution

Abstract

The invention discloses an intelligent vehicle urban intersection passing decision multi-objective optimization model based on conflict resolution. The intelligent vehicle urban intersection passing decision multi-objective optimization model is characterized by establishing a vehicle crossing interaction relationship judgment model by applying a fuzzy logic method according to crossing intentionof a target vehicle at an intersection and a driving type of a conflict vehicle, establishing a decision model for intersection conflict resolution based on the vehicle crossing interaction relationship judgment model, controlling the vehicles by taking acceleration as a decision variable, converting an intersection conflict resolution problem into a constrained multi-objective optimization problem, completing optimization of unmanned vehicle action generation results under different interaction modes of the intersection by introducing a variable cooperation coefficient, adopting an improved non-inferior genetic algorithm NSGA-II to solve a Pareto optimal solution set, then adopting entropy weight TOPSIS to carry out multi-attribute decision analysis on the Pareto optimal solution set, andselecting an optimal solution according to the preference of a decision maker. The intelligent vehicle urban intersection passing decision multi-objective optimization model optimizes the driving time and the driving speed of conflict vehicles, and improves the behavior decision-making level.

Description

technical field [0001] The invention belongs to the technical field of intelligent traffic system and intelligent vehicle research, and relates to the classification of driving interaction behaviors. The fuzzy logic method is used to establish a vehicle lane-changing interaction relationship judgment model and a vehicle crossing interaction relationship judgment model. The data can verify the effectiveness of the judgment model of intersection crossing interaction relationship, and help unmanned vehicles understand and judge the behavior of surrounding manned vehicles, which is of great significance to improve the level of autonomous driving of unmanned vehicles. Background technique [0002] The development of unmanned driving technology has become a global consensus, and it has great potential in solving traffic safety and managing traffic congestion. In 2014, the U.S. Department of Transportation proposed the "ITS Strategic Plan 2015-2019", which clarified that the develo...

AI Technical Summary

Problems solved by technology

It can be seen that the automatic driving function is not mature, and its decision-making control system still has potential safety hazards

[0004] In addition, in the U.S. DARPA Urban Challenge, "China Intelligent Vehicle Future Challenge Competition (IVFC)", "China Intelligent Vehicle Competition (CIVC)", and "World Intelligent Driving Challenge (WIDC)", when faced with interference from manned vehicles, Most of the participating cars adopt conservative driving behaviors such as slowing down or waiting to avoid conflicts, and do not consider the impact of dynamic interaction behaviors of other vehicles, ignoring the differential impact of interaction behaviors of different types of drivers, which will greatly limit the intersection of unmanned vehicles traffic potential

Images