When will it change the lane? A probabilistic regression approach for rarely occurring events

Schlechtriemen, Julian and Wirthmueller, Florian and Wedel, Andreas and Breuel, Gabi and Kuhnert, Klaus-Dieter (2015) When will it change the lane? A probabilistic regression approach for rarely occurring events. In: IEEE Intelligent Vehicles Symposium (IV), June 28 - July 1, 2015, Seoul, South Korea.

Full text not available from this repository.

Abstract

Understanding traffic situations in dynamic traffic environments is an essential requirement for autonomous driving. The prediction of the current traffic scene into the future is one of the main problems in this context. In this publication we focus on highway scenarios, where the maneuver space for traffic participants is limited to a small number of possible behavior classes. Even though there are many publications in the field of maneuver prediction, most of them set the focus on the classification problem, whether a certain maneuver is executed or not. We extend approaches which solve the classification problem of lane-change behavior by introducing the novel aspect of estimating a continuous distribution of possible trajectories. Our novel approach uses the probabilities which are assigned by a Random Decision Forest to each of the maneuvers lane following, lane change left and lane change right. Using measured data of a vehicle and the knowledge of the typical lateral movement of vehicles over time taken from realworlddata, we derive a Gaussian Mixture Regression method. For the final result we combine the predicted probability density functions of the regression method and the computed maneuver probabilities using a Mixture of Experts approach. In a large scale experiment on real world data collected on multiple test drives we trained and validated our prediction model and show the gained high prediction accuracy of the proposed method.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Vehicles, Trajectory, Probabilistic logic, Prediction algorithms, Training, Context, Vegetation
Subjects: DBIS Research > Publications
Divisions: Faculty of Engineering, Electronics and Computer Science > Institute of Databases and Informations Systems > DBIS Research and Teaching > DBIS Research > Publications
Depositing User: Michael Stach
Date Deposited: 21 Jun 2018 12:58
Last Modified: 18 May 2021 09:00
URI: http://dbis.eprints.uni-ulm.de/id/eprint/1622

Actions (login required)

View Item
View Item