Driving equipment decision making prediction method and device

Abstract

The invention relates to a driving equipment decision making prediction method. The method includes the steps that real-time environment information of driving equipment is obtained; and probability distribution of at least one action needing to be executed by the driving equipment is determined according to the real-time environment information and a prediction model, wherein the prediction modelis determined in advance according to sample data, and the characteristics of the sample data include the environment information and action information executed by a driver on the basis of the environment information. According to the method, the probability distribution of at least one action needing to be executed by the driving equipment can be predicted according to the real-time environmentinformation and the prediction model, and in other words, a prediction result is related to the probability distribution of the executed actions which are not a single action. On the one hand, the prediction result further accords with the actions actually executed by the driver, prediction accuracy is guaranteed, and therefore the driving equipment is effectively controlled; and on the other hand, convergence of the machine learning process can be guaranteed so that the prediction model can be determined.

Description

technical field [0001] The present invention relates to the technical field of control, in particular, to a method for predicting decision-making of driving equipment, a device for predicting decision-making of driving equipment, electronic equipment, and a computer-readable storage medium. Background technique [0002] In order to realize the automatic control of the driving device, it is necessary to predict the actions that the driving device needs to perform according to the environmental information of the driving device. In order to obtain a predictive model capable of making predictions, related technologies collect sample data including environmental information of driving equipment and actions performed by drivers based on the environmental information, and then perform machine learning based on the sample data to obtain a predictive model. [0003] According to the prediction model in the related art, an action can be determined based on the same environmental info...

AI Technical Summary

Problems solved by technology

[0005] On the one hand, this may cause the prediction results obtained according to the prediction model to be inconsistent with the actual situation, which may affect the accuracy of the prediction. The driver's actual actions in the data do not match, resulting in non-convergence of the machine learning process, making it impossible to determine the prediction model

Images