Self-learning Trajectory Prediction with Recurrent Neural Networks at Intelligent Intersections

Julian Bock, Jens Kotte, Markus Klösges, Till Beemelmanns

2017

Abstract

We present the concept and first results of a self-learning system for road user trajectory prediction at intersections with connected sensors. Infrastructure installed connected sensors can assist automated vehicles in perceiving the environment in complex urban scenes such as intersections. An intelligent intersection with connected sensors can measure the trajectories of road users using multiple sensor types and store the trajectories. Our approach uses this information to collect a large dataset of pedestrian trajectories. This dataset is again used to train a pedestrian prediction model with Recurrent Neural Networks. This model learns intersection specific pedestrian movement patterns. Through a self-learning process enabled by the measurements of connected sensors, the system continuously improves the prediction during operation while keeping the dataset preferably small. In this paper, we focus on the prediction of pedestrian trajectories, but as the approach is data-driven, the system could also predict other road users such as vehicles or bicyclists if trained with the respective data.

References

  1. Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., FeiFei, L. and Savarese, S. 'Social LSTM: Human Trajectory Prediction in Crowded Spaces' [online] http://vision.stanford.edu/pdf/CVPR16_N_LSTM.pdf.
  2. Brouwer, N., Kloeden, H. and Stiller, C. (2016) 'Comparison and evaluation of pedestrian motion models for vehicle safety systems', pp.2207-2212.
  3. Chollet, F. (2015) 'keras', GitHub repository.
  4. Consortium of Project SADA 'Project SADA'. http://www.projekt-sada.de/ (Accessed 26 January 2016).
  5. Graves, A. (2014) Generating Sequences With Recurrent Neural Networks. http://arxiv.org/pdf/1308.0850v5.
  6. Graves, A., Mohamed, A.-r. and Hinton, G. (2013) 'Speech recognition with deep recurrent neural networks', IEEE, pp.6645-6649.
  7. Helbing, D. (1990) 'Physikalische Modellierung des dynamischen Verhaltens von Fußgängern (Physical Modeling of the Dynamic Behavior of Pedestrians)78.
  8. Helbing, D. and Molnar, P. (1995) 'Social force model for pedestrian dynamics', Physical review E, Vol. 51, No. 5, p.4282.
  9. Hochreiter, S. (01.01.1991) Untersuchungen zu dynamischen neuronalen Netzen, diploma thesis, institut für informatik, lehrstuhl prof. brauer, technische universität münchen.
  10. Hochreiter, S. and Schmidhuber, J. (1997) 'Long short-term memory', Neural computation, Vol. 9, No. 8, pp.1735- 1780.
  11. I2EASE Consortium (2016) 'I2EASE Project'. http://www.cerm.rwth-aachen.de/i2ease (Accessed 26 January 2017).
  12. Käding, C., Rodner, E., Freytag, A. and Denzler, J. Active and Continuous Exploration with Deep Neural Networks and Expected Model Output Changes. http://arxiv.org/pdf/1612.06129v1.
  13. Keller, C.G. and Gavrila, D.M. (2014) 'Will the Pedestrian Cross? A Study on Pedestrian Path Prediction', IEEE Transactions on Intelligent Transportation Systems, Vol. 15, No. 2 [online] http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber= 6632960.
  14. Pellegrini, S., Ess, A., Schindler, K. and van Gool, L. (2009) 'You'll never walk alone: Modeling social behavior for multi-target tracking', pp.261-268.
  15. Rehder, E. and Kloeden, H. (2015) 'Goal-directed pedestrian prediction', pp.50-58.
  16. Robicquet, A., Sadeghian, A., Alahi, A. and Savarese, S. 'Learning Social Etiquette: Human Trajectory Understanding In Crowded Scenes', in , Computer Vision - ECCV 2016.
  17. Schneider, N. and Gavrila, D.M. (2013) 'Pedestrian path prediction with recursive Bayesian filters: A comparative study', Springer, pp.174-183.
  18. Sutskever, I., Vinyals, O. and Le V, Q. Sequence to Sequence Learning with Neural Networks. http://arxiv.org/pdf/1409.3215v3.
  19. The City of San Diego (09.03.2017) 'Smart City San Diego'.
  20. Wertheimer, R. and others (2014) 'Ko-PER Fahrerassistenz und präventive Sicherheit mittels kooperativer Perzeption: Partnerübergreifender Schlussbericht', schlussbericht, Bundesministerium für Wirtschaft und Technologie (BMWi).
  21. Xiao, T., Zhang, J., Yang, K., Peng, Y. and Zhang, Z. (2014) 'Error-driven incremental learning in deep convolutional neural network for large-scale image classification', ACM, pp.177-186.
Download


Paper Citation


in Harvard Style

Bock J., Kotte J., Beemelmanns T. and Klösges M. (2017). Self-learning Trajectory Prediction with Recurrent Neural Networks at Intelligent Intersections . In Proceedings of the 3rd International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS, ISBN 978-989-758-242-4, pages 346-351. DOI: 10.5220/0006374003460351


in Bibtex Style

@conference{vehits17,
author={Julian Bock and Jens Kotte and Till Beemelmanns and Markus Klösges},
title={Self-learning Trajectory Prediction with Recurrent Neural Networks at Intelligent Intersections},
booktitle={Proceedings of the 3rd International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,},
year={2017},
pages={346-351},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006374003460351},
isbn={978-989-758-242-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 3rd International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,
TI - Self-learning Trajectory Prediction with Recurrent Neural Networks at Intelligent Intersections
SN - 978-989-758-242-4
AU - Bock J.
AU - Kotte J.
AU - Beemelmanns T.
AU - Klösges M.
PY - 2017
SP - 346
EP - 351
DO - 10.5220/0006374003460351