Višeagentski sustav za potragu i spašavanje zasnovan na djelomično osmotrivim Markovljevim procesima odlučivanja

master's thesis

• Title (english): Multi-agent System for Search and Rescue based on Partially Observable Markov Decision Processes
• Author: Marijana Peti
• Mentor: Stjepan Bogdan (mentor)
• Committee member: Stjepan Bogdan (predsjednik povjerenstva)
• Committee member: Zdenko Kovačić (član povjerenstva)
• Committee member: Tamara Petrović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-09-04, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Slanje ljudi u spasilačke misije s vatrom predstavlja veliku opasnost po ljudski život, stoga je jednostavnije poslati tim robota koji će izvidjeti situaciju. Kako bi to autonomno mogli obaviti u ovom radu ispitan je algoritam djelomično osmotrivi Markovljevi procesi (POMDP) te je ispitano ponašanje uz djeljenje informacija zasnovano na konsenzus algoritmu. Ispitano je nekoliko modela POMDP-a te kako veličina prostora i broj agenata utječe na optimalan obilazak prostora i skraćivanja misije.

Abstract (english)

Sending people into the rescue missions with fire can be great danger for human being, so it may be more secure to send team of robots which will first scout the environment. In order to do that autonomously, in this thesis, algorithm Partially Observable Markov Decision Processes is being tested also with information sharing Consensus protocol. Several POMDP models were examined, also how the number of rooms and agents affects on optimal building tour and making the whole mission shorter.

• Keywords: POMDP; multi agentski sustav; bespilotne letjelice; detekcija vatre; misija; konsenzus
• Keywords (english): POMDP; multi agent system; unmanned aerial vehicle; fire detection; mission; consensus
• Language: english
• URN:NBN: urn:nbn:hr:168:904782
• Study programme: Title: Electrical Engineering and Information Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije (magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 13:28:43