Development of a dynamic path planning system for autonomous mobile robots in a flexible manufacturing system

Simple item page
dc.contributor.advisorLouw, Louisen_ZA
dc.contributor.advisorBitsch, Günteren_ZA
dc.contributor.authorFourie, Bradleyen_ZA
dc.contributor.otherStellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.en_ZA
dc.date.accessioned2023-02-03T20:15:52Zen_ZA
dc.date.accessioned2023-05-18T06:59:35Zen_ZA
dc.date.available2023-02-03T20:15:52Zen_ZA
dc.date.available2023-05-18T06:59:35Zen_ZA
dc.date.issued2023-02en_ZA
dc.descriptionThesis (MEng)--Stellenbosch University, 2023.en_ZA
dc.description.abstractENGLISH ABSTRACT: Recent developments in Industry 4.0 have shifted consumer demand, resulting in a need for manufacturers to supply small batches of highly customised products. To enable profitable highly-customised production, Autonomous Mobile Robots (AMRs) have become the most important technology associated with flexible material handling. However, path planning for AMRs in dynamic environments is an unsolved problem and remains to be the largest barrier to practical implementation. Currently, most AMR implementations in practice require manual reprogramming of waypoints. However, for Flexible Manufacturing Systems (FMSs), manual reprogramming is not feasible due to the flexible nature of the layouts and the large variety of disturbances that can occur at both the production and consumer levels. As a result, FMS environments require systems that can dynamically adapt AMR paths to prevent unplanned downtime, extra expenses, and manual labour required for manual waypoint reprogramming. In this thesis, a path planning system for AMRs that is suitable for dynamic manufacturing environments was developed. A design science research methodology was used to develop the path planning system, where both aspects of intelligent optimisation methods and Multi-Agent Systems (MASs) were investigated and developed for the final design. The dynamic path planning system utilised a MAS design in software, where the multirobot conflict avoidance mechanism was implemented using the Iterative Exclusion Principle (IEP). Moreover, several Genetic Algorithm (GA) and Reinforcement Learning (RL) methods were developed for the intelligent path optimisation algorithm of the path planning system, integrating aspects from the informed heuristic search literature. The RL algorithms used a curriculum learning process, where training was completed on mediumlevel hardware to improve algorithm convergence. However, the generalisability required for FMSs could not be achieved when restricting the training time to what is allowable between shift changes. The GA had superior performance after evaluation on three separate environments and a total of 150 different transport order configurations and was, therefore, selected for the final design. The dynamic path planning system was further developed into a technology demonstrator for evaluation in an accurate simulation model of theWerk150 logistics learning factory at the ESB Business School for validation. Several disturbance scenarios prevalent in the Werk150 facility were identified to validate the design, and the associated experiments were created to investigate various flexibility parameters. The technology demonstrator of the dynamic path planning system collaboratively planned conflict-free paths in all disturbance scenarios and enabled the material handling flexibility required for the Werk150 facility.en_ZA
dc.description.abstractAFRIKAANS OPSOMMING: Onlangse ontwikkelings in Industrie 4.0 vereis dat vervaardigers hoogs pasgemaakte produkte in klein eenhede produseer om aan verbruikersvraag te voldoen. Om hoogs pasgemaakte produksie moontlik te maak, het Outonome Mobiele Robotte (OMRe) die belangrikste tegnologie geword wat verband hou met buigsame materiaalhantering. Padbeplanning vir OMRe is egter ’n onopgeloste probleem en bly die grootste struikelblok vir praktiese implementering. Tans vereis die meeste OMR-implementerings in die praktyk handmatige herprogrammering van roetes. Vir Buigsame Vervaardigingstelsels (BVs) is handmatige herprogrammering egter nie prakties nie as gevolg van die buigsame aard van die uitlegte en die groot verskeidenheid van steurings wat kan voorkom. Gevolglik vereis BV-omgewings stelsels wat OMR-paaie dinamies kan aanpas om onbeplande stilstand, ekstra uitgawes en handearbeid wat nodig is vir handmatige herprogrammering van roetes te voorkom. In hierdie tesis was ’n padbeplanningstelsel vir OMRe ontwikkel wat geskik was vir dinamiese vervaardigingsomgewings. ’n Ontwerpwetenskap navorsingsmetodologie was geïmplementeer om die padbeplanningstelsel te ontwikkel, waar beide aspekte van intelligente optimeringsmetodes en Multi-Agent Stelsels (MASs) ondersoek was vir die finale ontwerp. Die dinamiese padbeplanningstelsel het ’n MAS-ontwerp in sagteware gebruik, waar die multi-robot konflikvermydingsmeganisme geïmplementeer is deur die uitsluitingsbeginsel te gebruik. Boonop is verskeie Genetiese Algoritme (GA) en Versterkingsleer (VL) metodes ontwikkel vir die intelligente padoptimeringsalgoritme van die padbeplanningstelsel, wat aspekte uit die ingeligte heuristiese soekliteratuur integreer. Die VL-algoritmes het ’n kurrikulumleerproses gebruik, waar opleiding op mediumvlak hardeware voltooi was om algoritme-konvergensie te verbeter. Die veralgemeenbaarheid wat vir FMSe vereis word, kon egter nie bereik word wanneer die opleidingstyd beperk was tot wat toelaatbaar is tussen skofveranderinge nie. Die GA het voortreflike werkverrigting gehad na evaluering op drie afsonderlike omgewings en ’n totaal van 150 verskillende vervoerbestelling-konfigurasies en is dus gekies vir die finale ontwerp. Die dinamiese padbeplanningstelsel is verder ontwikkel tot ’n tegnologiedemonstrator vir evaluering in ’n akkurate simulasiemodel van die Werk150 logistieke leerfabriek by die ESB Besigheidskool vir validering. Verskeie versteuringsscenario’s wat algemeen voorkom in die Werk150-fasiliteit was geïdentifiseer om die ontwerp te valideer, en die gepaardgaande eksperimente was geskep om verskeie uigsaamheidsparameters te ondersoek. Die tegnologie-demonstrator van die dinamiese padbeplanningstelsel het konflikvrye paaie in alle steuringscenario’s beplan en die materiaalhantering buigsaamheid moontlik gemaak wat vir die Werk150-fasiliteit vereis word.af_ZA
dc.description.versionMastersen_ZA
dc.format.extentxvii, 184 pages : illustrationsen_ZA
dc.identifier.urihttp://hdl.handle.net/10019.1/127001
dc.language.isoen_ZAen_ZA
dc.language.isoen_ZAen_ZA
dc.publisherStellenbosch : Stellenbosch Universityen_ZA
dc.publisherStellenbosch Universityen_ZA
dc.subject.lcshMultiagent systems -- South Africaen_ZA
dc.subject.lcshReinforcement learningen_ZA
dc.subject.lcshMobile robots -- Automationen_ZA
dc.subject.lcshGenetic algorithmsen_ZA
dc.titleDevelopment of a dynamic path planning system for autonomous mobile robots in a flexible manufacturing systemen_ZA
dc.typeThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
fourie_dynamic_2023.pdf
Size:
33.18 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Doctoral Degrees (Industrial Engineering)