Multi-Head Attention based Probabilistic Vehicle Trajectory Prediction

This paper presents online-capable deep learning model for probabilistic vehicle trajectory prediction. We propose a simple encoder-decoder architecture based on multihead attention. The proposed model generates the distribution of the predicted trajectories for multiple vehicles in parallel. Our approach to model the interactions can learn to attend to a few influential vehicles in an unsupervised manner, which can improve the interpretability of the network. The experiments using naturalistic trajectories at highway show the clear improvement in terms of positional error on both longitudinal and lateral direction.

[1]  Mooi Choo Chuah,et al.  GRIP: Graph-based Interaction-aware Trajectory Prediction , 2019, 2019 IEEE Intelligent Transportation Systems Conference (ITSC).

[2]  Thao Dang,et al.  Handling uncertainties in criticality assessment , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).

[3]  Silvio Savarese,et al.  Social LSTM: Human Trajectory Prediction in Crowded Spaces , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Nassir Navab,et al.  Attention-based Lane Change Prediction , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[5]  Ulrich Kressel,et al.  Probabilistic trajectory prediction with Gaussian mixture models , 2012, 2012 IEEE Intelligent Vehicles Symposium.

[6]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[7]  Chung Choo Chung,et al.  Sequence-to-Sequence Prediction of Vehicle Trajectory via LSTM Encoder-Decoder Architecture , 2018, 2018 IEEE Intelligent Vehicles Symposium (IV).

[8]  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).

[9]  Geoffrey E. Hinton,et al.  Layer Normalization , 2016, ArXiv.

[10]  Jianqiang Wang,et al.  Vehicle Trajectory Prediction by Integrating Physics- and Maneuver-Based Approaches Using Interactive Multiple Models , 2018, IEEE Transactions on Industrial Electronics.

[11]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[12]  Honglak Lee,et al.  Learning Structured Output Representation using Deep Conditional Generative Models , 2015, NIPS.

[13]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

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

[15]  Angelos Amditis,et al.  Sensor Fusion for Predicting Vehicles' Path for Collision Avoidance Systems , 2007, IEEE Transactions on Intelligent Transportation Systems.

[16]  Yi Zhang,et al.  Vehicle Trajectory Prediction Using Intention-based Conditional Variational Autoencoder , 2019, 2019 IEEE Intelligent Transportation Systems Conference (ITSC).

[17]  Florent Altché,et al.  An LSTM network for highway trajectory prediction , 2017, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).

[18]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[19]  Gert Kootstra,et al.  International Conference on Robotics and Automation (ICRA) , 2008, ICRA 2008.

[20]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[21]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[22]  John M. Dolan,et al.  Interactive Trajectory Prediction for Autonomous Driving via Recurrent Meta Induction Neural Network , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[23]  Philip H. S. Torr,et al.  DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).