LSTM-based Vehicle Type Classification using Real-time Trajectory Data in Automated Driving

In the era of automated driving, accurately understanding the behavior of surrounding vehicles is crucial for safe and efficient driving actions. Since each vehicle type exhibits a unique driving behavior, understanding other vehicles’ types and intentions enables AVs to make more informed decisions regarding predicting nearby vehicles’ future positions and actions. In this research, we implement a multi-layer LSTM model for vehicle type classification task using the trajectories of nearby vehicles in a traffic scene. The model takes the positions and actions of a vehicle over several time steps and outputs the probability distribution of vehicle classes. We test the model with HighD and NGSIM datasets and conduct performance evaluations. The findings reveal that the proposed model could accurately capture the vehicle classes from the vehicle’s driving behavior.