Automatic driving automobile track dynamic planning and tracking method based on transverse and longitudinal coordination

Abstract

The invention relates to an automatic driving automobile track dynamic planning and tracking method based on transverse and longitudinal coordination, the method comprises the following steps of firstly, intensively sampling a motion state in a Frenet space in which an automobile runs to finish transverse and longitudinal local track replanning; in transverse and longitudinal trajectory coordination planning, considering that the automobile in a complex traffic environment and static and dynamic obstacles in the environment cannot be simply equivalent to mass points; introducing a hyperplane theory to evaluate whether a vehicle track interferes with static and dynamic obstacles in a surrounding traffic environment or not and evaluate the risk of collision, and designing the track evaluation index systems such as smoothness, comfort and driving efficiency of the track to evaluate the track quality. In the trajectory tracking stage, a Brush tire model is adopted to design an automatic driving vehicle dynamics manipulation limit constraint rule, and the model predictive control (MPC) is utilized to complete automatic driving vehicle active steering (AFS) and direct yawing moment control (DYC) integrated trajectory tracking control.

Description

technical field [0001] The invention belongs to the field of intelligent transportation automatic driving vehicles, and in particular relates to a method for dynamic planning and tracking of automatic driving vehicle tracks based on horizontal and vertical coordination. Background technique [0002] As an important part of the intelligent transportation system, self-driving vehicles transform the closed loop of "human-vehicle-environment" in the traditional driving process into a "vehicle-environment" system. It can effectively replace the operation of human drivers, avoid human drivers' operational errors, and effectively improve the efficiency and safety of the transportation system. The research and development of autonomous vehicles has gradually attracted the attention of major domestic and foreign automobile manufacturers and research institutions. [0003] Self-driving cars perceive and identify the surrounding environment through external sensors such as cameras and ...

AI Technical Summary

Problems solved by technology

The algorithm based on numerical optimization is to transform the objective function and constraints into a convex optimization form, and then use the numerical optimization iterator to calculate its optimal solution. The biggest advantage of this method is that the optimal solution space is continuous, but the surrounding environment It is difficult to satisfy the condition of abstracting the objective function of convex optimization, and at the same time, solving the optimal solution often depends on the gradient iteration with high computational cost; these two types of methods are difficult to meet the high real-time requirements of autonomous driving

[0004] In addition, the current trajectory planning methods for autonomous vehicles are mostly aimed at the static obstacle scene of lateral motion planning, but in the actual driving scene of automatic driving is complex, there will be temporary obstacles and dynamic obstacles randomly, and the single lateral trajectory based on the static obstacle scene Planning is difficult to meet the high reliability requirements of autonomous driving. How to plan a horizontally and vertically coordinated dynamic trajectory of an autonomous vehicle in a comprehensive traffic environment that can cope with dynamic and static obstacles and meet the safety and comfort of unmanned vehicles and traffic efficiency

Images