| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Development of a methodology to calibrate a pedestrian microsimulation model : doctoral dissertation
Authors:ID Gruden, Chiara (Author)
ID Šraml, Matjaž (Mentor) More about this mentor... New window
ID Ištoka Otković, Irena (Comentor)
Files:.pdf DOK_Gruden_Chiara_2022.pdf (5,93 MB)
MD5: 4543FAEE553DC4E1D27231064FB8FF70
 
Language:English
Work type:Doctoral dissertation
Typology:2.08 - Doctoral Dissertation
Organization:FGPA - Faculty of Civil Engineering, Transportation Engineering and Architecture
Abstract:Walking, as a mode of transport, is becoming widespread, in a world, where urban conglomerates are broadening and becoming denser. Modern lifestyle trends on a side, and eco-friendly policies on the other, push people into walking habits, increasing the need for a suitable, attractive, accessible, connected and safe walking infrastructure. To reach such a result, it is necessary to understand, what are the needs of the users of this infrastructure, taking into consideration the behavioral specificities and the safety needs of pedestrians. In this process pedestrian microsimulation models, surrogate safety techniques, and technologies able to measure specific traits of pedestrian dynamics play a central role. The firsts allow to reproduce repeatedly in a virtual environment a specific infrastructure and to study the response of pedestrians. Nevertheless, to be accurate and efficient, they need to go through long and tedious calibration and validation processes, that are often seen as an important limitation by technicians. Surrogate safety techniques are methods, that are based on the concept, that it is possible to predict the safety level of a location, using near accidents. The main advantage of such techniques is that they are proactive. Till this moment, these techniques have been mainly applied to on-field measurements and are primarily centered on motorized road users. Less interest has been shown for vulnerable road users, especially for pedestrians, who have been less extensively studied. Finally, an element that could highly affect pedestrian safety is their reaction time. Nevertheless, its measurement has long been a big issue. Eye-tracking technology could be one of the solutions, allowing to analyze the directions and objects fixated by pedestrians. These listed issues are also the topics that are addressed by this research work. Focusing on the study of the action of pedestrians while crossing the road on an unsignalized crosswalk set on a roundabout entry leg, the dissertation thesis aims at studying the crossing time, reaction time and surrogate safety aspects typical of pedestrians at the recalled location. The main purpose of the research work is to develop a methodology to calibrate pedestrian Social Force Model at a selected location, using a specifically formulated neural network as a tool to fine-tune model's behavioral parameters. Eight parameters have been chosen to be fine-tuned, five of those are related to pedestrian behavior and three of them are related to car-following behavior. After the selection of input parameters, a feedforward network has been formulated. Its application in the framework of the whole calibration process has brought to considerably positive results, finding a combination of input parameters that improved the performance of the microsimulation model of 37 % in comparison to the default one. The outputs of the calibrated model have been used to calculate three measures of surrogate safety, and also in this case results demonstrated an improvement in the calculation of surrogate safety measures when using the calibrated outcomes in comparison to their calculation on the “default” model outputs. Finally, reaction time measurement and prediction have been addressed by the thesis, in order to be able to describe pedestrian crossing action in its completeness. Quantitative eye-tracking outputs have been the starting point for the calculation of pedestrian reaction time at different locations, and they allowed to create a database of behavioral, geometric, regulatory and flow characteristics, which was the foundation for the formulation of a new prediction model for pedestrian reaction time. The prediction model, which consists of a cascade-correlation neural network, gave a good response to the learning and generalization steps, turning a 74 % correlation between the measured reaction time values and the predicted ones, and being able to follow the variability of these values.
Keywords:pedestrian, microsimulation model, calibration, neural network, surrogate safety indicators, reaction time.
Place of publishing:Maribor
Place of performance:Maribor
Publisher:[C. Gruden]
Year of publishing:2022
Number of pages:[XIII] f., 184 str.
PID:20.500.12556/DKUM-81644 New window
UDC:656.142.021:[004.94+004.8](043.3)
COBISS.SI-ID:125215747 New window
Publication date in DKUM:03.10.2022
Views:781
Downloads:96
Metadata:XML RDF-CHPDL DC-XML DC-RDF
Categories:KTFMB - FG
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share


Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:04.05.2022

Secondary language

Language:Slovenian
Title:Razvoj metodologije za umerjanje mikro-simulacijskega modela za pešce
Abstract:V časih, ko se urbana naselja hitro širijo in število prebivalcev v njih strmo narašča, je hoja iz dneva v dan vse bolj priljubljen način mobilnosti. Sodobni življenjski slog po eni strani ter okolju-prijazne politike po drugi, spodbujajo ljudi k pešačenju. Posledica obojega je povečana težnja po primerni, privlačni, dostopni, povezani in varni infrastrukturi za hojo. Da bi to dosegli, moramo najprej razumeti dejanske potrebe uporabnikov te infrastrukture in upoštevati specifične vedenjske značilnosti in varnostne zahteve pešcev. V tem smislu igrajo prav posebno vlogo mikro-simulacijski modeli vedenja pešcev, tehnike nadomestne prometne varnosti ter tehnologije za merjenje določenih vidikov dinamike pešcev. Mikro-simulacija omogoča analizo vedenja pešcev na določeni infrastrukturi z možnostjo večkratnega reproduciranja njihovega odziva v virtualnem okolju. Da bi bil mikro-simulacijski model čim bolj natančen in verodostojen, mora iti skozi dolga in časovno zahtevna postopka kalibracije in validacije: ta dva procesa pa predstavljata za strokovnjake veliko omejitev. Tehnike nadomestne prometne varnosti so metode, ki temeljijo na dejstvu, da je mogoče oceniti raven prometne varnosti neke lokacije na podlagi »skoraj nesreč«. Glavna prednost teh metod je, da so proaktivne. Na tak način rešujejo etično težavo že utečenih tehnik, ki utemeljujejo svoje ugotovitve na nezgodah, ki so se že zgodile. Do zdaj so se te metode večinoma aplicirale na meritve realnega vedenja udeležencev v prometu in so se osredotočale predvsem na motorizirane udeležence. Ranljivi udeleženci prometa, še posebej pešci, so predstavljali manjši interes za raziskovanje. Ne nazadnje, je tudi reakcijski čas pešcev dejavnik, ki lahko močno vpliva na njihovo prometno varnost. Kljub temu, da je očitno reakcijski čas izredno pomemben dejavnik, je predstavljalo merjenje le-tega vedno veliko težavo. Problemu se v zadnjih časih lahko izognemo s pomočjo napredne tehnologije, kot je »eye-tracking«. Zgoraj navedena področja so teme, ki se jih dotika ta disertacija. Disertacija proučuje vedenje pešcev med prečkanjem ceste na nesemaforiziranem prehodu, ki je postavljen na vstopni krak krožišča. Čas prečkanja, reakcijski čas pešcev ter kazalniki nadomestne prometne varnosti so osnovni parametri, ki jih ta disertacija obravnava za analizo vedenja in varnosti pešcev na omenjeni lokaciji. Glavni cilj disertacije je razvoj metodologije za umerjanje modela socialnih moči na določeni lokaciji, z uporabo specifično izdelane nevronske mreže. Osredotočili smo se na osem parametrov, ki naj bi imeli pri kalibraciji največji vpliv: pet med temi je vezanih na vedenje pešcev, trije pa na vedenje voznikov. Na podlagi te izbire smo formulirali »feedforward« nevronsko mrežo. Aplikacija tako načrtovane nevronske mreže v kalibraciji je privedla do zelo spodbudnih rezultatov: z njo smo dosegli kombinacijo vhodnih parametrov, ki je izboljšala sposobnosti mikro-simulacijskega modela za celih 37% v primerjavi z rezultati »default« modela. Pridobljene rezultate kalibriranega modela smo uporabili za izračun treh kazalnikov nadomestne prometne varnosti. Tudi v tem primeru so kazalniki nadomestne prometne varnosti, izračunani na podlagi kalibriranega modela, potrdili boljše rezultate v primerjavi s tistimi, ki smo jih pridobili na podlagi izračunov »default« modela. Za celotno obravnavo dejanja prečkanja ceste smo merili tudi reakcijski čas pešcev. Na podlagi teh meritev smo ustvarili model za napoved le-tega. Kvantitativni rezultati eye-tracking-a so bili izhodiščna točka za izračun reakcijskega časa na različnih lokacijah. Ti so –skupaj s specifičnimi vedenjskimi značilnostmi pešcev in z lastnostmi obravnavanih lokacij– omogočili pripravo podatkovne baze za formulacijo modela napovedovanja. Model za napoved reakcijskega časa je »cascade-correlation« nevronska mreža. Z njo smo lahko napovedali reakcijski čas s 74% korelacije in smo pridobili dobre odzive na precej variabilne vrednosti reakcijskega časa.
Keywords:pešci, mikro-simulacijski model, kalibracija, nevronska mreža, kazalniki nadomestne prometne varnosti, reakcijski čas.


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica