Planiranje gibanja mobilnog robota u strukturiranom stakleniku

master's thesis

• Title (english): Motion planning for a mobile robot in a structured greenhouse
• Author: Filip Bradarić
• Mentor: Matko Orsag (mentor)
• Committee member: Matko Orsag (predsjednik povjerenstva)
• Committee member: Zdenko Kovačić (član povjerenstva)
• Committee member: Damjan Miklić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-16, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

U ovom diplomskom radu opisan je postupak optimizacije prostora automatiziranog staklenika i izgradnje mreže putanja za navigaciju mobilnog robota. U diskretiziranom prostoru staklenika potrebno je rasporediti različite kulture biljaka na optimalne pozicije pri čemu je potrebno zadovoljiti ograničenja broja i dostupnosti biljaka te povezanosti slobodnog prostora. Za optimizaciju prostora staklenika osmišljen je genetski algoritam. U optimiziranom prostoru primijenjen je algoritam automatske izgradnje mreže putanja. Valjanost i složenost algoritama analizirane su eksperimentalno. Eksperimentom provedenim u realističnom simulacijskom okruženju potvrđena je prilagođenost optimiziranog rasporeda staklenika za navigaciju mobilnog robota.

Abstract (english)

This thesis describes a procedure for optimizing an autonomous greenhouse layout and generating a feasible roadmap for robot navigation. In a discretized greenhouse layout, it is necessary to place different plant cultures at optimal positions, simultaneously satisfying plant number and accessibility constraints as well as preserving free space connectivity. A genetic algorithm for greenhouse layout optimization is described. An algorithm of automatic roadmap generation is developed and applied to the optimized greenhouse layout. The validity and complexity of the algorithms are analyzed experimentally. An experiment performed in a realistic 3D simulator demonstrates that a differential drive mobile robot is able to localize itself and navigate in the optimized greenhouse layout.

• Keywords: višekriterijska optimizacija; genetski algoritam; mreža putanja
• Keywords (english): multi-objective optimization; genetic algorithm; roadmap
• Language: croatian
• URN:NBN: urn:nbn:hr:168:188703
• 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 09:48:20