Data-driven simulation of pedestrian collision avoidance with a nonparametric neural network
"Data-driven simulation of pedestrian dynamics is an incipient and promising approach for building reliable microscopic pedestrian models. We propose a methodology based on generalized regression neural networks, which does not have to deal with a huge number of free parameters as in the case o...
Guardado en:
Autores principales: | , |
---|---|
Formato: | Artículos de Publicaciones Periódicas acceptedVersion |
Lenguaje: | Inglés |
Publicado: |
2020
|
Materias: | |
Acceso en línea: | http://ri.itba.edu.ar/handle/123456789/2230 |
Aporte de: |
id |
I32-R138-123456789-2230 |
---|---|
record_format |
dspace |
spelling |
I32-R138-123456789-22302022-12-07T13:06:13Z Data-driven simulation of pedestrian collision avoidance with a nonparametric neural network Martin, Rafael F. Parisi, Daniel PEATONES DINAMICA SIMULACION NAVEGACION REDES NEURONALES INTELIGENCIA ARTIFICIAL "Data-driven simulation of pedestrian dynamics is an incipient and promising approach for building reliable microscopic pedestrian models. We propose a methodology based on generalized regression neural networks, 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. Experimental data were collected in a motion capture laboratory providing high-precision trajectories. The proposed model allows us to simulate the trajectory of a pedestrian avoiding an obstacle from any direction. Together with the methodology specifications, we provide the data set needed for performing the simulations of this kind of pedestrian dynamic system." 2020-06-26T20:35:59Z 2020-06-26T20:35:59Z 2020-02 Artículos de Publicaciones Periódicas info:eu-repo/semantics/acceptedVersion 0925-2312 http://ri.itba.edu.ar/handle/123456789/2230 en info:eu-repo/semantics/altIdentifier/doi/10.1016/j.neucom.2019.10.062 info:eu-repo/grantAgreement/PID/2015-0003/AR. Ciudad Autónoma de Buenos Aires info:eu-repo/grantAgreement/ITBACyT/2018-42/AR. Ciudad Autónoma de Buenos Aires application/pdf |
institution |
Instituto Tecnológico de Buenos Aires (ITBA) |
institution_str |
I-32 |
repository_str |
R-138 |
collection |
Repositorio Institucional Instituto Tecnológico de Buenos Aires (ITBA) |
language |
Inglés |
topic |
PEATONES DINAMICA SIMULACION NAVEGACION REDES NEURONALES INTELIGENCIA ARTIFICIAL |
spellingShingle |
PEATONES DINAMICA SIMULACION NAVEGACION REDES NEURONALES INTELIGENCIA ARTIFICIAL Martin, Rafael F. Parisi, Daniel Data-driven simulation of pedestrian collision avoidance with a nonparametric neural network |
topic_facet |
PEATONES DINAMICA SIMULACION NAVEGACION REDES NEURONALES INTELIGENCIA ARTIFICIAL |
description |
"Data-driven simulation of pedestrian dynamics is an incipient and promising approach for building reliable microscopic pedestrian models. We propose a methodology based on generalized regression neural networks, 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. Experimental data were collected in a motion capture laboratory providing high-precision trajectories. The proposed model allows us to simulate the trajectory of a pedestrian avoiding an obstacle from any direction. Together with the methodology specifications, we provide the data set needed for performing the simulations of this kind of pedestrian dynamic system." |
format |
Artículos de Publicaciones Periódicas acceptedVersion |
author |
Martin, Rafael F. Parisi, Daniel |
author_facet |
Martin, Rafael F. Parisi, Daniel |
author_sort |
Martin, Rafael F. |
title |
Data-driven simulation of pedestrian collision avoidance with a nonparametric neural network |
title_short |
Data-driven simulation of pedestrian collision avoidance with a nonparametric neural network |
title_full |
Data-driven simulation of pedestrian collision avoidance with a nonparametric neural network |
title_fullStr |
Data-driven simulation of pedestrian collision avoidance with a nonparametric neural network |
title_full_unstemmed |
Data-driven simulation of pedestrian collision avoidance with a nonparametric neural network |
title_sort |
data-driven simulation of pedestrian collision avoidance with a nonparametric neural network |
publishDate |
2020 |
url |
http://ri.itba.edu.ar/handle/123456789/2230 |
work_keys_str_mv |
AT martinrafaelf datadrivensimulationofpedestriancollisionavoidancewithanonparametricneuralnetwork AT parisidaniel datadrivensimulationofpedestriancollisionavoidancewithanonparametricneuralnetwork |
_version_ |
1765660767245303808 |