prikaz prve stranice dokumenta Potporno učenje za robotske manipulatore
No public access
undergraduate thesis
Potporno učenje za robotske manipulatore
2019. urn:nbn:hr:168:021228
Baković, Luka
University of Zagreb
Faculty of Electrical Engineering and Computing

Cite this document

Baković, L. (2019). Potporno učenje za robotske manipulatore (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:021228

Baković, Luka. "Potporno učenje za robotske manipulatore." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:021228

Baković, Luka. "Potporno učenje za robotske manipulatore." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:021228

Baković, L. (2019). 'Potporno učenje za robotske manipulatore', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 11 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:021228

Baković L. Potporno učenje za robotske manipulatore [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2019 [cited 2024 November 11] Available at: https://urn.nsk.hr/urn:nbn:hr:168:021228

L. Baković, "Potporno učenje za robotske manipulatore", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:168:021228

Please login to the repository to save this object to your list.
Metadata
TitlePotporno učenje za robotske manipulatore
Title (english)Reinforcement learning for robotic manipulators
AuthorLuka Baković
MentorIvan Petrović (mentor)
Committee memberIvan Petrović (predsjednik povjerenstva)
Committee memberMario Brčić (član povjerenstva)
Committee memberFilip Marić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2019-07-12, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Abstract
Set alata za potporno učenje spojen je sa simulatorom fizike kako bi dao cjelovit sustav za simuliranje agenata koji kontroliraju robotičke manipulatore. Vodi se rasprava o teoretskim implikacijama te opisom zadane konstrukcije. Rezultati dokazaju funkcionalnost zamišljenog koncepta, dva različita algoritma daju konvergentne politike odlučivanja za robota sa zadaćom dolaska na traženo mjesto u prostoru. Daljnja istraživanja su moguća u smjeru uređivanja okoline za potporno učenje i isprobavanje različitih algoritama
Abstract (english)
A reinforcement learning API is combined with a physics simulator to make a pipeline for simulating agents controlling robotic manipulators. Theoretical implications are discussed, followed by the description of such a construction. Results serve as a proof of concepts, with two different algorithms providing convergent policies for a robot tasked with reaching a target point. Further research is discussed, mostly aimed at further customising the environment and trying out different algorithms.
Keywords
Keywords (english)
Languageenglish
URN:NBNurn:nbn:hr:168:021228
Study programmeTitle: Electrical Engineering and Information Technology
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2020-01-07 16:26:32