Prediction of Lane Change Intentions of Human Drivers using an LSTM, a CNN and a Transformer

TL;DR

This paper compares LSTM, CNN, and Transformer models for predicting human lane change intentions, finding that Transformers outperform the others and are less prone to overfitting, with accuracy up to 96.73%.

Contribution

It provides a comparative analysis of three neural network architectures for lane change prediction and evaluates how input data choices affect performance.

Findings

Transformers outperform LSTM and CNN in prediction accuracy.

Transformer models are less affected by overfitting.

Prediction accuracy ranges from 82.79% to 96.73%.

Abstract

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.