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

IEEE Robotics and Automation Letters, vol. 6, pp. 2357–2364

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 letter 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.

Authors 5

1. Florian Wirthmüller

   Mercedes-Benz (Germany) · Universität Ulm

   Affiliation as printed

   Institute of Databases and Information Systems (DBIS), Ulm University, Ulm, Germany

   Mercedes-Benz AG, Böblingen, Germany

2. Marvin Klimke Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, Aachen, Germany

3. Julian Schlechtriemen

   Mercedes-Benz (Germany) · University of Siegen

   Affiliation as printed

   Institute of Realtime Learning Systems, University of Siegen, Siegen, Germany

   Mercedes-Benz AG, Böblingen, Germany

4. Jochen Hipp

   Mercedes-Benz (Germany)

   Affiliation as printed

   Mercedes-Benz AG, Böblingen, Germany

5. Manfred Reichert

   Universität Ulm

   Affiliation as printed

   Institute of Databases and Information Systems (DBIS), Ulm University, Ulm, Germany