Estimation of Discretized Motion of Pedestrians by the Decision-Making Model

TL;DR

This paper introduces a method to analyze pedestrian decision-making during egress by estimating a Markov decision process from trajectory data, enabling optimization of individual movement strategies based on specific goals.

Contribution

It presents a novel approach to extract pedestrian decisions from trajectory data and estimates a Markov decision process for use in optimizing individual agent strategies.

Findings

Successfully estimates pedestrian decision processes from experimental trajectories.

Demonstrates how to optimize a pedestrian's movement strategy for different objectives.

Provides a framework for integrating decision-making models into pedestrian simulation.

Abstract

The contribution gives a micro-structural insight into the pedestrian decision process during an egress situation. A method how to extract the decisions of pedestrians from the trajectories recorded during the experiments is introduced. The underlying Markov decision process is estimated using the finite mixture approximation. Furthermore, the results of this estimation can be used as an input to the optimization of a Markov decision process for one `clever' agent. This agent optimizes his strategy of motion with respect to different reward functions, minimizing the time spent in the room or minimizing the amount of inhaled CO.