Predicting the Time Until a Vehicle Changes the Lane Using LSTM-based Recurrent Neural Networks

TL;DR

This paper presents an LSTM-based system for accurately predicting the time until surrounding vehicles change lanes on highways, achieving high accuracy up to 3.5 seconds before the maneuver.

Contribution

Develops a novel LSTM-based approach for predicting lane change timing, improving temporal prediction accuracy over previous methods.

Findings

Root mean squared error around 0.7 seconds

Predictions become highly accurate 3.5 seconds before lane change

Median error less than 0.25 seconds 3.5 seconds prior

Abstract

To plan safe and comfortable trajectories for automated vehicles on highways, accurate predictions of traffic situations are needed. So far, a lot of research effort has been spent on detecting lane change maneuvers rather than on estimating the point in time a lane change actually happens. In practice, however, this temporal information might be even more useful. This paper deals with the development of a system that accurately predicts the time to the next lane change of surrounding vehicles on highways using long short-term memory-based recurrent neural networks. An extensive evaluation based on a large real-world data set shows that our approach is able to make reliable predictions, even in the most challenging situations, with a root mean squared error around 0.7 seconds. Already 3.5 seconds prior to lane changes the predictions become highly accurate, showing a median error of less than 0.25 seconds. In summary, this article forms a fundamental step towards downstreamed highly accurate position predictions.