Show simple item record

Kodizajn arhitekture i algoritama za lokalizacijumobilnih robota i detekciju prepreka baziranih namodelu

dc.contributor.advisorRaković, Mirko
dc.contributor.advisorDevy, Michel
dc.contributor.otherBorovac, Branislav
dc.contributor.otherAkil, Mohamed
dc.contributor.otherObradović, Đorđe
dc.contributor.otherPiat, Jonathan
dc.contributor.otherRaković, Mirko
dc.contributor.otherDevy, Michel
dc.creatorTertei, Daniel
dc.date.accessioned2017-01-23T10:50:30Z
dc.date.available2017-01-23T10:50:30Z
dc.date.available2020-07-03T14:07:47Z
dc.date.issued2016-12-02
dc.identifier.urihttp://nardus.mpn.gov.rs/handle/123456789/7425
dc.identifier.urihttp://www.cris.uns.ac.rs/DownloadFileServlet/Disertacija147402386613115.pdf?controlNumber=(BISIS)101781&fileName=147402386613115.pdf&id=6888&source=NaRDuS&language=srsr
dc.identifier.urihttp://www.cris.uns.ac.rs/record.jsf?recordId=101781&source=NaRDuS&language=srsr
dc.identifier.urihttp://www.cris.uns.ac.rs/DownloadFileServlet/IzvestajKomisije147402389370177.pdf?controlNumber=(BISIS)101781&fileName=147402389370177.pdf&id=6889&source=NaRDuS&language=srsr
dc.description.abstractThis thesis proposes SoPC (System on a Programmable Chip) architectures for efficient embedding of vison-based localization and obstacle detection tasks in a navigational pipeline on autonomous mobile robots. The obtained results are equivalent or better in comparison to state-ofthe- art. For localization, an efficient hardware architecture that supports EKF-SLAM's local map management with seven-dimensional landmarks in real time is developed. For obstacle detection a novel method of object recognition is proposed - detection by identification framework based on single detection window scale. This framework allows adequate algorithmic precision and execution speeds on embedded hardware platforms.en
dc.description.abstractOva teza bavi se dizajnom SoPC (engl. System on a Programmable Chip) arhitektura i algoritama za efikasnu implementaciju zadataka lokalizacije i detekcije prepreka baziranih na viziji u kontekstu autonomne robotske navigacije. Za lokalizaciju, razvijena je efikasna računarska arhitektura za EKF-SLAM algoritam, koja podržava skladištenje i obradu sedmodimenzionalnih orijentira lokalne mape u realnom vremenu. Za detekciju prepreka je predložena nova metoda prepoznavanja objekata u slici putem prozora detekcije fiksne dimenzije, koja omogućava veću brzinu izvršavanja algoritma detekcije na namenskim računarskim platformama.sr
dc.languageen
dc.publisherУниверзитет у Новом Саду, Факултет техничких наукаsr
dc.rightsopenAccessen
dc.sourceУниверзитет у Новом Садуsr
dc.subjectRobot navigationen
dc.subjectRobotska navigacijasr
dc.subjectvisual SLAMen
dc.subjectvisual obstacle detectionen
dc.subjecthw/sw co-designen
dc.subjectSoPCen
dc.subjectheterogeneous embedded boardsen
dc.subjectvizuelni SLAMsr
dc.subjectdetekcija prepreka u slicisr
dc.subjectkodizajn hardver/softversr
dc.subjectSoPCsr
dc.subjectheterogene namenske pločicesr
dc.titleCo-design of architectures and algorithms for mobile robot localization and model-based detection of obstaclesen
dc.title.alternativeKodizajn arhitekture i algoritama za lokalizacijumobilnih robota i detekciju prepreka baziranih namodelusr
dc.typedoctoralThesisen
dc.rights.licenseBY-NC-ND
dcterms.abstractРаковић Мирко; Девy Мицхел; Боровац Бранислав; Aкил Мохамед; Обрадовић Ђорђе; Пиат Јонатхан; Раковић Мирко; Девy Мицхел; Тертеи Даниел;
dc.identifier.fulltexthttp://nardus.mpn.gov.rs/bitstream/id/41807/IzvestajKomisije7354.pdf
dc.identifier.fulltexthttp://nardus.mpn.gov.rs/bitstream/id/41808/Disertacija7354.pdf


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record