Data-driven simulationMartin, Rafael F.Parisi, Daniel R.Data-driven simulation of pedestrian dynamicsPedestrian dynamics is an incipient and promising approach for building reliable microscopic pedestrian models. We propose a methodology based on generalized regression neural networksGeneralized Regression Neural Network (GRNN), which does not have to deal with a huge number of free parameters as in the case of multilayer neural networks. Although the method is general, we focus on the one pedestrian—one obstacle problem. The proposed model allows us to simulate the trajectory of a pedestrian avoiding an obstacle from any direction.
Data-Driven Simulation for Pedestrians Avoiding a Fixed Obstacle
Springer Proceedings Phys.
2020-11-17
6 pages
Article/Chapter (Book)
Electronic Resource
English
Steering , Data-driven simulation , Pedestrian dynamics , Generalized regression neural network , Artificial intelligence , Navigation Physics and Astronomy , Soft and Granular Matter, Complex Fluids and Microfluidics , Complex Systems , Computer Appl. in Social and Behavioral Sciences , Statistical Physics and Dynamical Systems , Physics , Transportation Technology and Traffic Engineering
Data-Driven Simulation for Pedestrians Avoiding a Fixed Obstacle
British Library Conference Proceedings | 2020
|Data-Driven Simulation for Pedestrians Avoiding a Fixed Obstacle
TIBKAT | 2020
|Intelligent control system and method for avoiding pedestrians
European Patent Office | 2020
|