Modeliranje ponašanja pješaka u blizini pješačkih prijelaza temeljeno na Markovljevim lancima

master's thesis

• Title (english): Markov chain-based modelling of pedestrian crossing behavior at unsignalized crosswalks
• Author: Ivana Starčević Ratković
• Mentor: Branimir Škugor (mentor)
• Committee member: Tomislav Stipančić (predsjednik povjerenstva)
• Committee member: Filip Šuligoj (član povjerenstva)
• Committee member: Branimir Škugor (član povjerenstva)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2022-12-15, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering

Abstract

Iako su brojni zadaci autonomne vožnje niže razine u dobroj mjeri riješeni, autonomna vožnja u prisutnosti ostalih sudionika u prometu, kao što su primjerice pješaci i biciklisti, još uvijek predstavlja značajan izazov. Stoga je precizno modeliranje njihovog ponašanja i integracija pripadnih modela u simulacijska okruženja za autonomnu vožnju od presudne važnosti za razvoj autonomnih vozila. U sklopu diplomskog rada obrađena je problematika modeliranja ponašanja pješaka u blizini pješačkih prijelaza temeljena na snimljenim podacima. Pritom je proveden pregled literature na tu temu te su izdvojeni najčešći pokazatelji koji se koriste u pripadnim analizama. Za potrebe modeliranja i dobivanje osnovnih uvida odabran je javno dostupan skup snimljenih podataka koji sadrži značajan broj interakcija vozila i pješaka. Modeliranje ponašanja pješaka s obzirom na odabrane snimljene podatke provedeno je korištenjem metode Markovljevih lanaca, gdje je pripadna matrica prijelaznih vjerojatnosti implementirana u obliku rijetke matrice temeljene na rječniku ključeva u svrhu smanjenja zahtjeva na memoriju i poboljšanje računalne učinkovitosti. Provedena je i validacija izvedenog modela korištenjem Monte Carlo simulacija s obzirom na snimljene podatke. Naposlijetku je razmotrena mogućnost primjene dobivenog modela za optimalno upravljanje brzinom vozila koje prilazi pješačkom prijelazu s pješacima te je iznesen zaključak i mogućnost dodatnog usavršavanja modela.

Abstract (english)

Although many tasks of lower-level autonomous driving have been solved to a good extent, autonomous driving in the presence of other road users such as pedestrians and cyclists still represents a significant challenge. Therefore, precise modeling of their behavior and integration of related models into simulation environments for autonomous driving is of crucial importance for the development of autonomous vehicles. As part of the thesis, the issue of modeling pedestrian behavior near pedestrian crossings based on recorded data was addressed. At the same time, a review of the literature on the subject was carried out, and the most common indicators used in related analyzes were singled out. For the purposes of modeling and obtaining basic insights, a publicly available set of recorded data containing a significant number of vehicle-pedestrian interactions was selected. Pedestrian behavior modeling with regard to selected recorded data was carried out using the Markov chain method, where the associated matrix of transition probabilities was implemented in the form of a sparse matrix based on a dictionary of keys in order to reduce memory requirements and improve computing efficiency. Validation of the derived model was also carried out using Monte Carlo simulations with respect to recorded data. Finally, the possibility of applying the obtained model for optimal control of the speed of vehicles approaching a crosswalk with pedestrians was considered, and the conclusion as well as the possibility of additional refinement of the model were presented.

• Keywords: Markovljevi lanci; modeliranje; Monte Carlo simulacije; pješaci
• Keywords (english): Markov chains; modeling; Monte Carlo simulations; pedestrians
• Language: croatian
• URN:NBN: urn:nbn:hr:235:204334
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2022-12-19 11:46:48