Prediction of Lane Change Intentions of Human Drivers using an LSTM, a CNN and a Transformer
This work addresses a specific safety and efficiency issue for automated vehicles, but it is incremental as it compares existing architectures on a known dataset.
The paper tackled the problem of predicting lane change intentions of human drivers to improve automated vehicle safety and efficiency, achieving accuracies ranging from 82.79% to 96.73% with transformer networks performing best and being less prone to overfitting.
Lane changes of preceding vehicles have a great impact on the motion planning of automated vehicles especially in complex traffic situations. Predicting them would benefit the public in terms of safety and efficiency. While many research efforts have been made in this direction, few concentrated on predicting maneuvers within a set time interval compared to predicting at a set prediction time. In addition, there exist a lack of comparisons between different architectures to try to determine the best performing one and to assess how to correctly choose the input for such models. In this paper the structure of an LSTM, a CNN and a Transformer network are described and implemented to predict the intention of human drivers to perform a lane change. We show how the data was prepared starting from a publicly available dataset (highD), which features were used, how the networks were designed and finally we compare the results of the three networks with different configurations of input data. We found that transformer networks performed better than the other networks and was less affected by overfitting. The accuracy of the method spanned from $82.79\%$ to $96.73\%$ for different input configurations and showed overall good performances considering also precision and recall.