Predicting the Time Until a Vehicle Changes the Lane Using LSTM-based Recurrent Neural Networks
This work provides more accurate temporal predictions of lane changes for automated vehicles, which is crucial for safer and more comfortable trajectory planning.
This paper addresses the problem of predicting the time until a vehicle changes lanes on highways. The developed system, based on LSTM-based recurrent neural networks, achieves a root mean squared error of approximately 0.7 seconds, with predictions becoming highly accurate (median error < 0.25 seconds) 3.5 seconds before the lane change.
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.