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

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.

[1]  Joachim Denzler,et al.  Active and Continuous Exploration with Deep Neural Networks and Expected Model Output Changes , 2016, ArXiv.

[2]  Yuxin Peng,et al.  Error-Driven Incremental Learning in Deep Convolutional Neural Network for Large-Scale Image Classification , 2014, ACM Multimedia.

[3]  Silvio Savarese,et al.  Learning Social Etiquette: Human Trajectory Understanding In Crowded Scenes , 2016, ECCV.

[4]  Dariu Gavrila,et al.  UvA-DARE ( Digital Academic Repository ) Pedestrian Path Prediction with Recursive Bayesian Filters : A Comparative Study , 2013 .

[5]  Christoph Stiller,et al.  Comparison and evaluation of pedestrian motion models for vehicle safety systems , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[6]  Alex Graves,et al.  Generating Sequences With Recurrent Neural Networks , 2013, ArXiv.

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

[8]  Dirk Helbing Physikalische Modellierung des dynamischen Verhaltens von Fußgängern (Physical Modeling of the Dynamic Behavior of Pedestrians) , 1990 .

[9]  John Salvatier,et al.  Theano: A Python framework for fast computation of mathematical expressions , 2016, ArXiv.

[10]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[11]  Luc Van Gool,et al.  You'll never walk alone: Modeling social behavior for multi-target tracking , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[12]  C. G. Keller,et al.  Will the Pedestrian Cross? A Study on Pedestrian Path Prediction , 2014, IEEE Transactions on Intelligent Transportation Systems.

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

[14]  Sepp Hochreiter,et al.  Untersuchungen zu dynamischen neuronalen Netzen , 1991 .

[15]  Helbing,et al.  Social force model for pedestrian dynamics. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[16]  Eike Rehder,et al.  Goal-Directed Pedestrian Prediction , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

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