Prediction of human driving behavior using deep learning: a recurrent learning structure

Predicting the intentions of the human and the machine on a near future is required to the human-machine shared control of automated intelligent vehicles. The autonomous system is able to inform about its future intentions, however it is not possible for the human to provide this information, it is necessary then to predict it. This paper proposes a deep learning methodology to predict human navigation intentions in a time horizon of a few seconds, using a recurrent neural network (RNN) architecture based on the Long Short-Term Memory (LSTM) architecture. Taking as input various preprocessed and non-preprocessed data, generated by embedded sensors and the intrinsic data of the vehicle, the proposed model predicts the future linear and angular velocities of the vehicle. The model was trained and tested on a dataset created from real data from our cars equipped with sensors (LiDAR, camera), in different scenarios and road types. Furthermore, a data sensitive study is presented evaluating the effects of missing data in the learning process.