# Data-driven simulation of pedestrian collision avoidance with a nonparametric neural network

## TL;DR

This paper introduces a data-driven pedestrian collision avoidance simulation using a nonparametric neural network, specifically generalized regression neural networks, to accurately model pedestrian trajectories avoiding obstacles.

## Contribution

It presents a novel approach employing generalized regression neural networks for pedestrian simulation, reducing complexity compared to multilayer neural networks.

## Key findings

- The model accurately simulates pedestrian trajectories avoiding obstacles.
- High-precision experimental data supports the model's effectiveness.
- The approach is adaptable to various directions of obstacle avoidance.

## Abstract

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.