Driving strategy model training method and device

Abstract

The invention aims at providing a driving strategy model training method and device. The method comprises acquiring model parameter information corresponding to a driving strategy model of a driving device, wherein the model parameter information is determined by training the driving strategy model on the basis of preset driving rule information, and the driving strategy model is established on the basis on reinforcement learning algorithms; acquiring the driving parameter information of the driving device during a driving process, and based on the model parameter information, training the driving strategy model. Compared with the prior art, the driving strategy model training method avoids exploration from scratch on training the driving strategy model, instead, the driving device can drive just like having learnt driving rules before training starts, so that the training process of the driving strategy model on the basis can be greatly shortened, and meanwhile, the number of times ofunreasonable driving strategies as well as damage to vehicles during the training process can be greatly reduced.

Description

technical field [0001] The present application relates to the field of automatic driving, and in particular to a technology for training a driving strategy model. Background technique [0002] With the development and application of machine learning technology, for example, the development of reinforcement learning technology, in the existing automatic driving technology, for vehicles, especially the driving control of automatic driving vehicles, the reinforcement learning neural network trained by reinforcement learning algorithm To achieve this, the real-time state information of the vehicle is input to the reinforcement learning neural network, thereby outputting the corresponding driving strategy information. However, in the existing training of the reinforcement learning neural network, for each vehicle that needs to be trained, It is necessary to continuously train the corresponding neural network parameters from scratch. However, in practical applications, for differe...

AI Technical Summary

Problems solved by technology

[0002] With the development and application of machine learning technology, for example, the development of reinforcement learning technology, in the existing automatic driving technology, for vehicles, especially the driving control of automatic driving vehicles, the reinforcement learning neural network trained by reinforcement learning algorithm To achieve this, the real-time state information of the vehicle is input to the reinforcement learning neural network, thereby outputting the corresponding driving strategy information. However, in the existing training of the reinforcement learning neural network, for each vehicle that needs to be trained, It is necessary to continuously train the corresponding neural network parameters from scratch. However, in practical applications, for different vehicles, due to the different vehicle parameters (vehicle length, weight, wheelbase, parts, etc.), the corresponding neural network parameters Different, if a reinforcement learning training from scratch is required for each car, it will require a long training and trial-and-error process, which will bring huge training costs

Moreover, a lot of training and trial and error, if applied to the actual vehicle, will consume a long time and cause huge damage to the vehicle body

Images