Model-predictive planning for autonomous vehicles anticipating intentions of vulnerable road users by artificial neural networks

This article presents a hierarchical path planning framework that allows to generate plans for autonomous vehicles in the presence of vulnerable road users (VRUs), such as pedestrians and cyclists. Contrasting many existing approaches, the hierarchical approach allows not only to resolve emergency situations, but also to consider regular settings. Planning is based on model predictive control (MPC), which allows to make optimal, anticipatory decisions based on forecasts of the intentions of VRUs while explicitly accounting for constraints. The VRU trajectory forecast is based on a polynomial least-squares approximation of the VRU's trajectories in combination with a multilayer perceptron artificial neural network for prediction over a future horizon. The efficacy of the proposed framework is demonstrated for two example scenarios.

[1]  A. Ferrara.  Automatic pre-crash collision avoidance in cars , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[2]  W. Marsden.  I and J , 2012 .

[3]  Aaas News,et al.  Book Reviews , 1893, Buffalo Medical and Surgical Journal.

[4]  Thia Kirubarajan,et al.  Estimation with Applications to Tracking and Navigation: Theory, Algorithms and Software , 2001 .

[5]  Steven M. LaValle,et al.  Planning algorithms , 2006 .

[6]  Hans B. Pacejka,et al.  Tire and Vehicle Dynamics , 1982 .

[7]  Olaf Stursberg,et al.  Cooperation of autonomous vehicles using a hierarchy of auction-based and model-predictive control , 2016, 2016 IEEE Intelligent Vehicles Symposium (IV).

[8]  Michael Goldhammer,et al.  Trajectory prediction of cyclists using a physical model and an artificial neural network , 2016, 2016 IEEE Intelligent Vehicles Symposium (IV).

[9]  H. P. Williams,et al.  Model Building in Mathematical Programming , 1979 .

[10]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[11]  Klaus C. J. Dietmayer,et al.  Intersection-Based Road User Tracking Using a Classifying Multiple-Model PHD Filter , 2014, IEEE Intelligent Transportation Systems Magazine.

[12]  Marko Bacic,et al.  Model predictive control , 2003 .

[13]  Stefan Hahn,et al.  Nonlinear lateral vehicle control in combined emergency steering and braking maneuvers , 2016, 2016 IEEE Intelligent Vehicles Symposium (IV).

[14]  Florent Altché,et al.  Optimal trajectory planning for autonomous driving integrating logical constraints: An MIQP perspective , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[15]  Konrad Doll,et al.  Cyclists' starting behavior at intersections , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

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

[17]  David González,et al.  A Review of Motion Planning Techniques for Automated Vehicles , 2016, IEEE Transactions on Intelligent Transportation Systems.

[18]  Vicente Milanés Montero,et al.  Autonomous Pedestrian Collision Avoidance Using a Fuzzy Steering Controller , 2011, IEEE Transactions on Intelligent Transportation Systems.

[19]  Dariu Gavrila,et al.  Context-Based Pedestrian Path Prediction , 2014, ECCV.

[20]  B. Sick,et al.  Track-Based Forecasting of Pedestrian Behavior by Polynomial Approximation and Multilayer Perceptrons , 2016 .

[21]  Carlos Bordons Alba,et al.  Model Predictive Control , 2012 .

[22]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[23]  Olaf Stursberg,et al.  Cooperative driving using a hierarchy of mixed-integer programming and tracking control , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[24]  Richard C. Larson,et al.  Model Building in Mathematical Programming , 1979 .

[25]  Klaus C. J. Dietmayer,et al.  Cooperative multi sensor network for traffic safety applications at intersections , 2012, 2012 15th International IEEE Conference on Intelligent Transportation Systems.

[26]  Ulrich Brunsmann,et al.  Autonomous evasive maneuvers triggered by infrastructure-based detection of pedestrian intentions , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[27]  Georg Bretthauer,et al.  Invariant Trajectory Tracking With a Full-Size Autonomous Road Vehicle , 2010, IEEE Transactions on Robotics.

[28]  Darren Liccardo,et al.  Automatic collision avoidance using model-predictive online optimization , 2012, 2012 IEEE 51st IEEE Conference on Decision and Control (CDC).