0468093 20240103213245.120170102235959.9 10.1007/978-3-319-33482-0_40 8 P cav_un_epca*0468092978-3-319-33481-3313-320ChamSpringer International Publishing2016KnoopVictor L.DaamenWinnie pedestrian motion statistical analysis Markov decision process cav_un_auth*0307172 Hrabák Pavel Adaptivní systémy Department of Adaptive Systems AS AS UTIA-B Department of Adaptive Systems CZ Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0313524 Ticháček O. CZ cav_un_auth*0263972 Sečkárová Vladimíra Adaptivní systémy Department of Adaptive Systems AS AS UTIA-B Department of Adaptive Systems CZ Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2016/AS/hrabak-0468093.pdf cav_un_auth*0292725 GA13-13502S GA ČR 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. cav_un_auth*0340161 Conference on Traffic and Granular Flow ‘15 20151027 Nootdorp NL 20151030 BD 2017 3 RVO:67985556 http://hdl.handle.net/11104/0269414 S 2016 SCOPUS PUBMED WOS cav_un_epca*0468092 Traffic and Granular Flow '15 978-3-319-33481-3 313 320 Cham Springer International Publishing 2016 Knoop Victor L. 340 Daamen Winnie 340