Tracked vehicle slip rate estimation method capable of obtaining estimation uncertainty

Abstract

The invention relates to a tracked vehicle slip rate estimation method capable of obtaining estimation uncertainty, and belongs to the field of slip rate estimation. The method comprises the following steps: firstly, collecting a large amount of data by using a crawler-type platform, then establishing a slip rate discrete estimation model, and finally establishing a slip rate regression model based on sparse Gaussian process regression; and the input characteristics of the slip rate discrete estimation model and the slip rate regression model are driving wheel torque and rotating speed, vehicle transverse and longitudinal acceleration, and vehicle yaw velocity and pitch velocity. The method is based on segmented sparse Gaussian process regression, and can be applied to tracked vehicles to obtain estimation uncertainty; according to the invention, through segmented sparse Gaussian process regression, the time complexity of training of the slip rate discrete estimation model and the slip rate regression model is reduced; the slip rate discrete estimation model is high in accuracy, and the slip rate regression model is small in overall error; and the method can be further applied to tracked vehicle model correction and traction force control.

Description

technical field [0001] The invention relates to a method for estimating the slip rate of a tracked vehicle capable of obtaining estimation uncertainty, in particular to a method for estimating the slip rate of a tracked vehicle based on segmental sparse Gaussian process regression, which belongs to the field of slip rate estimation. Background technique [0002] Compared with wheeled vehicles, tracked vehicles have stronger steering ability and passability, making them play an important role in both military and civilian fields. During the running of a tracked vehicle, the track needs to perform compound motion: on the one hand, it needs to move along with the vehicle body in a straight line relative to the ground. q On the other hand, the crawler has to do a rotational movement relative to the car body, and this movement speed is called the relative speed, expressed as v x Indicates that the slip rate σ=(v x -v q ) / v x Indicates the difference between the two velocities...

AI Technical Summary

Problems solved by technology

This method is a promising method, but there are still some limitations: first, it only considers low-speed and straight-going conditions, and does not consider high-speed and turning conditions; second, it only estimates single-wheel slip, without Consider the difference in the slippage of multiple wheels; third, only for wheeled vehicles, whether it is applicable to tracked vehicles remains to be investigated

In addition, the training time complexity of the Gaussian process regression method is O(n3), and n is the number of training samples. Therefore, when the training set is large, the time cost of this method will be very high. high, making it difficult to apply to tasks with large datasets

Images