Automatic driving vehicle trajectory tracking system and method based on neural network dynamics model

Abstract

The invention discloses an automatic driving vehicle trajectory tracking system and method based on a neural network dynamics model, and the system comprises a neural network vehicle dynamics model part, a vehicle dynamics data collection part (including a CarSim simulation data acquisition process based on a driving simulator and a virtual simulation platform, and real world automatic driving vehicle data acquisition), and a vehicle trajectory tracking part. A neural network model training part; and a model prediction control algorithm design part. According to the method, the established neural network vehicle dynamics prediction model is combined with the model prediction control algorithm, and compared with an end-to-end control algorithm, the proposed control algorithm has higher interpretability. In addition, tracking control of an expected track can be achieved under different road conditions and driving working conditions, the path tracking precision is guaranteed, meanwhile, transverse and longitudinal stability is considered, and a high-performance motion controller is developed for an automatic driving vehicle.

Description

technical field [0001] The invention relates to the technical field of automatic driving of intelligent vehicles, in particular to a trajectory tracking system and method for automatic driving vehicles based on a neural network dynamics model. Background technique [0002] With the continuous upgrading of the "new four modernizations" of automobiles and the rapid development of artificial intelligence technology, autonomous vehicles have become the trend of traditional automobile industry transformation and the research focus of world vehicle engineering. Self-driving vehicles promise to free people from tedious long-distance driving, and there is great potential to reduce traffic congestion and reduce traffic accidents. Autonomous vehicles are usually composed of environment perception, path planning and control execution systems, in which the construction of vehicle models is crucial for trajectory planning and control, and is the basis for high-safety and high-reliability...

AI Technical Summary

Problems solved by technology

Although this method reduces the computational complexity, the vehicle dynamics model usually cannot fully consider the vertical motion of the vehicle, the suspension motion characteristics, and the longitudinal and lateral coupling relationship of the tire force when the vehicle is running at high speed.

Therefore, when the vehicle is driving at high speed, a large trajectory tracking error will occur, which cannot meet the actual needs of high-level automatic driving of intelligent vehicles.

Images