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

0468093 - ÚTIA 2017 RIV CH eng C - Conference Paper (international conference)
Hrabák, Pavel - Ticháček, O. - Sečkárová, Vladimíra
Estimation of Discretized Motion of Pedestrians by the Decision-Making Model.
Traffic and Granular Flow '15. Cham: Springer International Publishing, 2016 - (Knoop, V.; Daamen, W.), s. 313-320. ISBN 978-3-319-33481-3.
[Conference on Traffic and Granular Flow ‘15. Nootdorp (NL), 27.10.2015-30.10.2015]
R&D Projects: GA ČR GA13-13502S
Institutional support: RVO:67985556
Keywords : pedestrian motion * statistical analysis * Markov decision process
Subject RIV: BD - Theory of Information
http://library.utia.cas.cz/separaty/2016/AS/hrabak-0468093.pdf

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 optimisation of a Markov decision process for one ‘clever’ agent. This agent optimises his strategy of motion with respect to different reward functions, minimising the time spent in the room or minimising the amount of inhaled CO.
Permanent Link: http://hdl.handle.net/11104/0269414