Unmanned tracked vehicle and trajectory tracking control method and system thereof

Abstract

The invention relates to an unmanned tracked vehicle and a trajectory tracking control method and system thereof, and belongs to the technical field of vehicle trajectory tracking control. The method comprises the following steps: firstly, forming an MPC model based on an objective function of a trajectory tracking controller generated based on a kinematic model of the unmanned tracked vehicle and a constraint function of the trajectory tracking controller generated based on the objective function and a kinetic model of the unmanned tracked vehicle; after a reference trajectory is generated according to pose features of the unmanned tracked vehicle, curvature features of a road and real-time working condition state information, the reference trajectory and vehicle trajectory tracking response state information are input into an MPC model to obtain a parameter combination, then the parameter combination is input into an MLP neural network to obtain a control parameter, and finally, the control parameter is obtained. And tracking control of the track of the unmanned tracked vehicle is completed according to the control parameters, so that the working condition adaptability of track tracking of the unmanned tracked vehicle is effectively improved, and the track tracking precision, the vehicle driving stability and the calculation time cost are well balanced.

Description

technical field [0001] The invention relates to the technical field of vehicle track tracking control, in particular to an unmanned tracked vehicle and a track tracking control method and system thereof. Background technique [0002] In recent years, ground unmanned platforms have been used more and more in port transportation, epidemic prevention and control, field search and rescue, and battlefield environments. As a key technology for unmanned driving, trajectory tracking control has also been developed more and more. The attention of scholars, among which the control method based on model prediction is widely used. However, most of the current trajectory tracking control methods are based on fixed parameters, and it is difficult to guarantee the tracking accuracy and stability of the vehicle under complex and variable working conditions. Based on this, some scholars have proposed adaptive parameter adjustment methods, including more accurate online estimation of vehicle...

AI Technical Summary

Problems solved by technology

Since the interaction relationship between the ground and the track is difficult to accurately characterize under off-road conditions, it is difficult to provide stable and reliable input for the system based on the online estimation of vehicle model parameters, and the online estimation requires high real-time resource allocation of the system

Some research results use MPC as the basic framework to improve trajectory tracking performance by adding feedforward, data learning, etc., but lack of verification on the actual high-speed crawler platform

Images