Vehicle Driving Intent Recognition Based on Enhanced Bidirectional Long Short-Term Memory Network

In the context of high-speed mixed traffic and intricate multi-vehicle interaction, existing driving intention recognition models for research vehicles inadequately address crucial factors, such as style vehicle-vehicle interaction information. This paper introduces a novel model based on an enhanced bidirectional long- short-term memory network (Bi LSTM). The proposed leverages trajectory sequence target vehicle, style, features surrounding inputs effective training learning. It facilitates classification feature dataset, specifically considering diverse styles. Additionally, whale optimization algorithm is employed to optimize pivotal hyperparameters, encompassing number hidden layer nodes learning rate, effectively mitigating adverse impacts manual parameter adjustment. model's efficacy validated using NGSIM exhibiting impressive accuracy 97.5% in precisely identifying vehicle intentions.