Decision planning method for intelligent driving of automobile on ice and snow covered pavement

Abstract

The invention relates to a decision planning method for intelligent driving of an automobile on an ice and snow pavement. The method mainly comprises the following steps: step 1, a decision method of a hierarchical state machine is designed by considering lane changing safety distance and driver dissatisfaction degree accumulation in an ice and snow environment; 2, planning an expected path based on an ice and snow environment improved mixed A * planning algorithm; and 3, optimizing the generated path by adopting a cubic spline interpolation method, and planning a smooth trajectory.

Description

technical field [0001] The invention relates to the design of a humanized advanced driving assistance system (ADAS), in particular to an environment-based intelligent driving vehicle decision-making planning method. Background technique [0002] The ice and snow environment has long existed in the vast regions of my country's northeast and northwest, and vehicles in cold regions have long existed in the special working conditions of the ice and snow environment. In regions such as the Northeast and Northwest, the winter is long, the temperature is low, and the snowfall is heavy. Before the snow is cleared, the driving conditions of the car drivers are very poor. After clearing the roads, some residual snow will also be left behind. Under the action of the ice and snow environment, the traffic operation environment is harsh, and the road surface adhesion coefficient is only 1 / 8 to 1 / 4 of the normal road surface. The driver's driving comfort becomes poor, and it is easy to pr...

AI Technical Summary

Problems solved by technology

The method based on sampling has the problem of high solution complexity, and the sampling efficiency is low in some boundary scenes

Zhang Yu et al. applied a hybrid A* algorithm and a conjugate gradient descent path smoother to generate a smooth path by dynamically expanding the four-node pattern. Compared with A*, a kinematic model was introduced so that each graph obtained The side is that the generated trajectory is smoother, and its disadvantage is that it lacks an obstacle avoidance module and does not consider surrounding obstacles

Jorge Godoy et al. designed a local path planning module based on the path optimal decision-making method. This module interacts with the global path planning module and has the functions of generating smooth fitting trajectories and avoiding static and dynamic obstacles. The disadvantage is that there are The problem of high time complexity

Images