Graph Neural Networks for Modelling Traffic Participant Interaction

By interpreting a traffic scene as a graph of interacting vehicles, we gain a flexible abstract representation which allows us to apply Graph Neural Network (GNN) models for traffic prediction. These naturally take interaction between traffic participants into account while being computationally efficient and providing large model capacity. We evaluate two state-of-the art GNN architectures and introduce several adaptations for our specific scenario. We show that prediction error in scenarios with much interaction decreases by 30 % compared to a model that does not take interactions into account. This suggests that interaction is important, and shows that we can model it using graphs. This makes GNNs a worthwhile addition to traffic prediction systems.

[1]  Thierry Fraichard,et al.  Motion prediction for moving objects: a statistical approach , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[2]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[3]  Franz Kummert,et al.  Behavior prediction at multiple time-scales in inner-city scenarios , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).

[4]  Alex Pentland,et al.  Coupled hidden Markov models for complex action recognition , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  F. Scarselli,et al.  A new model for learning in graph domains , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[6]  Helbing,et al.  Congested traffic states in empirical observations and microscopic simulations , 2000, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[7]  Lutz Eckstein,et al.  The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[8]  Gereon Hinz,et al.  Designing a far-reaching view for highway traffic scenarios with 5G-based intelligent infrastructure , 2017 .

[9]  Mathias Perrollaz,et al.  Learning-based approach for online lane change intention prediction , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[10]  Stephan Günnemann,et al.  Pitfalls of Graph Neural Network Evaluation , 2018, ArXiv.

[11]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[12]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[13]  Alois Knoll,et al.  Deep neural networks for Markovian interactive scene prediction in highway scenarios , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[14]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[15]  Mykel J. Kochenderfer,et al.  Analysis of Recurrent Neural Networks for Probabilistic Modeling of Driver Behavior , 2017, IEEE Transactions on Intelligent Transportation Systems.

[16]  Mykel J. Kochenderfer,et al.  Factor graph scene distributions for automotive safety analysis , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[17]  Heinrich Müller,et al.  SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[18]  Gerd Wanielik,et al.  Comparison and evaluation of advanced motion models for vehicle tracking , 2008, 2008 11th International Conference on Information Fusion.

[19]  Mykel J. Kochenderfer,et al.  Imitating driver behavior with generative adversarial networks , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[20]  Martin Buss,et al.  Interactive scene prediction for automotive applications , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[21]  M. Treiber,et al.  Estimating Acceleration and Lane-Changing Dynamics Based on NGSIM Trajectory Data , 2007 .

[22]  Dizan Vasquez,et al.  A survey on motion prediction and risk assessment for intelligent vehicles , 2014, ROBOMECH Journal.