prikaz prve stranice dokumenta Artificial intelligence-based methods for interaction force estimation and mediated navigation of a robot manipulator on a mobile base
Access restricted to students and staff of home institution
doctoral thesis
Artificial intelligence-based methods for interaction force estimation and mediated navigation of a robot manipulator on a mobile base
2022. urn:nbn:hr:179:803092
Kružić, Stanko
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Cite this document

Kružić, S. (2022). Artificial intelligence-based methods for interaction force estimation and mediated navigation of a robot manipulator on a mobile base (Doctoral thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:803092

Kružić, Stanko. "Artificial intelligence-based methods for interaction force estimation and mediated navigation of a robot manipulator on a mobile base." Doctoral thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:803092

Kružić, Stanko. "Artificial intelligence-based methods for interaction force estimation and mediated navigation of a robot manipulator on a mobile base." Doctoral thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:803092

Kružić, S. (2022). 'Artificial intelligence-based methods for interaction force estimation and mediated navigation of a robot manipulator on a mobile base', Doctoral thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 19 April 2024, https://urn.nsk.hr/urn:nbn:hr:179:803092

Kružić S. Artificial intelligence-based methods for interaction force estimation and mediated navigation of a robot manipulator on a mobile base [Doctoral thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2022 [cited 2024 April 19] Available at: https://urn.nsk.hr/urn:nbn:hr:179:803092

S. Kružić, "Artificial intelligence-based methods for interaction force estimation and mediated navigation of a robot manipulator on a mobile base", Doctoral thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:179:803092

Please login to the repository to save this object to your list.
Metadata
TitleArtificial intelligence-based methods for interaction force estimation and mediated navigation of a robot manipulator on a mobile base
Title (croatian)Metode umjetne inteligencije za procjenu sila interakcije i medijacijsku navigaciju robotskog manipulatora na mobilnoj platformi
AuthorStanko Kružić https://orcid.org/0000-0003-0756-6982
MentorJosip Musić (mentor)
Committee memberVladan Papić https://orcid.org/0000-0002-1873-6353 (predsjednik povjerenstva)
Committee memberMirjana Bonković (član povjerenstva)
Committee memberTamara Grujić (član povjerenstva)
Committee memberZdenko Kovačić https://orcid.org/0000-0003-3987-4576 (član povjerenstva)
Committee memberJanez Podobnik https://orcid.org/0000-0001-9359-0297 (član povjerenstva)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2022-03-18, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Automation and Robotics
Universal decimal classification
(UDC)		621.3 - Electrical engineering
Abstract
Mobile robotic manipulators have recently emerged and are today found in industrial and domestic environments. They can perform various tasks due to their ability to move in space. Since they consist of a mobile base on which a robotic manipulator is mounted, the knowledge of both mobile robots and robotic manipulators is required to control it eectively. Thus, ecient control schemes for both mobile base and manipulator need to be developed. This dissertation tackles both fields and proposes solutions to common problems in them. First, an ecient and modular control scheme that achieves the complex behaviour of the mobile base is developed. It is achieved using fuzzy mediation to fuse two simple behaviours (navigation to a given goal and obstacle avoidance). Also, an approach to obstacle avoidance based on neural networks is developed and successfully incorporated into the fuzzy mediation scheme. In the experiments, the approaches demonstrated good performance in navigation on two real-world robots of dierent sizes and shapes. Furthermore, approaches (based on neural networks) are proposed to estimate the end-eector forces acting on the manipulator and to estimate joint-side torques by using the sensor mounted under the robot base. The networks were trained for two manipulators of dierent sizes and payloads. They generalised well to unseen trajectories, and force and torque estimates are reasonably accurate.
Abstract (croatian)
Mobilni robotski manipulatori su se pojavili tek nedavno, a već ih se može naći u industrijskim okolinama i domovima. Mogu obavljati razne zadatke zbog svoje mogućnosti kretanja u prostoru. Budući da se sastoje od mobilne baze na koju je montiran standardni robotski manipulator, potrebno je znanje iz područja mobilnih robota i robotskih manipulatora da bi se efikasno upravljalo takvim složenim sustavom. Stoga je potrebno razviti efikasne upravljačke sheme za mobilne platforme i za robotske manipulatore. Ova disertacija obuhvaća oba polja i predlaže rješenja za česte probleme u njima. Prvo je razvijena efikasna i modularna upravljačka shema koja ostvaruje kompleksno ponašanje mobilnog robota. To se postiže korištenjem medijacije temeljene na neizrazitoj logici, u cilju fuzije dva jednostavna ponašanja (navigacija i izbjegavanje prepreka). Također je razvijena i metoda za izbjegavanje prepreka temeljena na neuronskim mrežama, te uspješno ugrađena u shemu medijacije. U provedenim eksperimentima, dva stvarna robota različitih veličina i oblika su pokazala dobre performanse u navigaciji na dva stvarna robota različitih velična i oblika. Nadalje, predloženi su i razvijeni pristupi za procjenu sila koje djeluju na vrh robotskog manipulatora, te za procjenu momenata u zglobovima robota. Oba pristupa se temelje na neuronskim mrežama i koriste mjerenje senzora koji je postavljen ispod baze robota. Mreže su trenirane za dva manipulatora različitih veličina i nosivosti. One dobro generaliziraju za nepoznate trajektorije, te su procjene sila na vrhu i momenata u zglobovima prilično točne.
Keywords
Keywords (croatian)
Languageenglish
URN:NBNurn:nbn:hr:179:803092
Promotion2022
Study programmeTitle: Electrical Engineering and Information Technology
Study programme type: university
Study level: postgraduate
Academic / professional title: doktor/doktorica znanosti, područje tehničkih znanosti, polje elektrotehnika (doktor/doktorica znanosti, područje tehničkih znanosti, polje elektrotehnika)
Type of resourceText
Extent133 str.
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2022-04-27 08:05:46