Method for prejudging behaviors of surrounding vehicles of unmanned vehicle

The invention relates to the technical field of prediction of behaviors of other unmanned vehicles, and provides a method for predicting behaviors of surrounding vehicles of an unmanned vehicle. Firstly, track data and environment data of a target vehicle are acquired; feature value addition and standardization processing are carried out on the track data, lane changing and straight moving track data are extracted, category labeling is carried out, data within the time period with the length of dk are randomly extracted, and a kLSTM data set is formed; performing data cleaning on the environment data, extracting lane change and straight-going environment data, and performing category labeling to obtain an RF data set; constructing and training a kLSTM deep neural network model and a randomforest model for behavior pre-judgment of surrounding vehicles, and performing behavior pre-judgment on the target vehicle in combination with the random forest model, the first LSTM deep neural network model and the second