Okruženje za simulaciju sustava za upravljanje promjenjivim ograničenjem brzine na urbanim autocestama zasnovanih na učenju

master's thesis

• Title (english): Framework for Simulation of Variable Speed Limit Control Systems on Urban Motorways Based on Learning
• Author: Krešimir Kušić
• Mentor: Edouard Ivanjko (mentor)
• Committee member: Sadko Mandžuka (predsjednik povjerenstva)
• Committee member: Luka Novačko (član povjerenstva)
• Committee member: Hrvoje Gold (član povjerenstva)
• Granter: University of Zagreb; Faculty of Transport and Traffic Sciences; (Division of Intelligent Transport Systems and Logistics); (Department of Intelligent Transport Systems); Zagreb
• Defense date and country: 2017-07-04, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Traffic and Transport Technology; Intelligent Transport Systems and Logistics

Abstract

U uvjetima povećane prometne potražnje na urbanim autocestama javlja se potreba za uvođenjem upravljanja prometom s ciljem prevencije i smanjenja posljedica nastajanja prometnih zagušenja. Jedno od rješenja iz područja inteligentnih transportnih sustava je sustav za upravljanje ograničenjem brzine na urbanim autocestama. Noviji pristup u upravljanju promjenjivim ograničenjem brzine na urbanim autocestama koristi algoritme zasnovane na učenju. U radu je opisano upravljanje prometom na urbanim autocestama zasnovano na upravljanju promjenjivim ograničenjem brzine, analizirana je mogućnost primjene učenja s posebnim naglaskom na algoritmu Q-učenja u upravljanju promjenjivim ograničenjem brzine te je izrađeno okruženje za simulaciju takvog upravljanja korištenjem mikroskopskog simulatora VISSIM i programskog paketa MATLAB.

Abstract (english)

In the conditions of increased traffic demand on urban motorways, there is a need for dynamic traffic management. Its aim is preventing and reducing the consequences of traffic congestion on urban motorways. One of the acceptable solutions is the application of services from the domain of Intelligent Transport System. One of such services is variable speed limit control (VSLC). The newer approach to managing variable speed limitation on urban motorways utilizes “algorithm based on learning”. This master’s thesis describes dynamic traffic management on urban motorways that is based on VSLC. In addition, it describes the ability to apply learning for VSLC with an emphasis on the Q-learning algorithm. An environment for simulating such system is developed using the microscopic simulator VISSIM and the MATLAB software package.

• Keywords: upravljanje promjenjivim ograničenjem brzine; simulacijsko okruženje; algoritmi zasnovani na učenju
• Keywords (english): variable speed limit control; framework for simulation; reinforcement learning; Q-learning
• Language: croatian
• URN:NBN: urn:nbn:hr:119:016117
• Study programme: Title: Intelligent Transport Systems and Logistics; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka prometa (magistar/magistra inženjer/inženjerka prometa)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2017-07-11 13:36:35