TY  - CONF
AU  - Jevtić, Đorđe
AU  - Miljković, Zoran
AU  - Petrović, Milica
AU  - Jokić, Aleksandar
PY  - 2023
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/6896
AB  - One of the significant aspects for enabling the intelligent behavior to the Unmanned Aerial Vehicles (UAVs) is by providing an algorithm for navigation through the dynamic and unseen environment. Therefore, to be autonomous, they need sensors to perceive their surroundings and utilize gathered information to decide which action to take. Having that in mind, in this paper, the authors designed the system for obstacle avoidance and also investigate the elements of the Markov decision process and their influence on each other. The flying mobile robot used within the considered problem is quadrotor type and has an integrated Lidar sensor which is utilized to
detect obstacles. The sequential decision-making model based on Q-learning is trained within the MATLAB Simulink environment. The simulation results demonstrate that the UAV can navigate through the environment in most algorithm runs without colliding with surrounding obstacles.
PB  - ETRAN Society, The Society for Electronics, Telecommunications, Computing, Automatics and Nuclear engineering supported by IEEE
C3  - Proceedings of the 10th International Conference on Electrical, Electronics and Computing Engineering (IcETRAN 2023)
T1  - Reinforcement Learning-based Collision Avoidance for UAV
EP  - 6
IS  - 5496
SP  - 1
UR  - https://hdl.handle.net/21.15107/rcub_machinery_6896
ER  - 

@conference{
author = "Jevtić, Đorđe and Miljković, Zoran and Petrović, Milica and Jokić, Aleksandar",
year = "2023",
abstract = "One of the significant aspects for enabling the intelligent behavior to the Unmanned Aerial Vehicles (UAVs) is by providing an algorithm for navigation through the dynamic and unseen environment. Therefore, to be autonomous, they need sensors to perceive their surroundings and utilize gathered information to decide which action to take. Having that in mind, in this paper, the authors designed the system for obstacle avoidance and also investigate the elements of the Markov decision process and their influence on each other. The flying mobile robot used within the considered problem is quadrotor type and has an integrated Lidar sensor which is utilized to
detect obstacles. The sequential decision-making model based on Q-learning is trained within the MATLAB Simulink environment. The simulation results demonstrate that the UAV can navigate through the environment in most algorithm runs without colliding with surrounding obstacles.",
publisher = "ETRAN Society, The Society for Electronics, Telecommunications, Computing, Automatics and Nuclear engineering supported by IEEE",
journal = "Proceedings of the 10th International Conference on Electrical, Electronics and Computing Engineering (IcETRAN 2023)",
title = "Reinforcement Learning-based Collision Avoidance for UAV",
pages = "6-1",
number = "5496",
url = "https://hdl.handle.net/21.15107/rcub_machinery_6896"
}

Jevtić, Đ., Miljković, Z., Petrović, M.,& Jokić, A.. (2023). Reinforcement Learning-based Collision Avoidance for UAV. in Proceedings of the 10th International Conference on Electrical, Electronics and Computing Engineering (IcETRAN 2023)
ETRAN Society, The Society for Electronics, Telecommunications, Computing, Automatics and Nuclear engineering supported by IEEE.(5496), 1-6.
https://hdl.handle.net/21.15107/rcub_machinery_6896

Jevtić Đ, Miljković Z, Petrović M, Jokić A. Reinforcement Learning-based Collision Avoidance for UAV. in Proceedings of the 10th International Conference on Electrical, Electronics and Computing Engineering (IcETRAN 2023). 2023;(5496):1-6.
https://hdl.handle.net/21.15107/rcub_machinery_6896 .

Jevtić, Đorđe, Miljković, Zoran, Petrović, Milica, Jokić, Aleksandar, "Reinforcement Learning-based Collision Avoidance for UAV" in Proceedings of the 10th International Conference on Electrical, Electronics and Computing Engineering (IcETRAN 2023), no. 5496 (2023):1-6,
https://hdl.handle.net/21.15107/rcub_machinery_6896 .

TY  - CONF
AU  - Miljković, Zoran
AU  - Jevtić, Đorđe
PY  - 2022
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/3823
AB  - In recent years, the development of deep learning models that can generate more accurate predictions and operate in real-time has brought both opportunities and challenges across the various domains of robotic vision. This breakthrough enables researchers to design and deploy more challenging tasks on intelligent mobile robots, which require emphasized abilities of learning and reasoning. In this paper, a new method for intelligent robot control, based on deep learning and reinforcement learning is proposed. The fundamental idea of this work is how the UAV equipped with a monocular camera can learn significant information about the object of interest in the context of its localization and navigation. For such purpose, the object detection system based on Tiny YOLOv2 architecture is employed. Furthermore, bounding box data generated by a convolution neural network is utilized for depth estimation and determining object boundaries. This information has shown how the state-space dimensions can be significantly reduced, which was essential for further implementation of the Q-learning algorithm. In order to test the proposed framework, a model is developed in MATLAB Simulink. The simulation, which covered different scenarios, was carried out on the UAV within the 3D scene rendered by Unreal Engine. The obtained results have demonstrated the applicability of the proposed methodology for depth estimation, gathering information about the object, object-driven navigation, and autonomous localization and navigation.
PB  - Springer Science and Business Media Deutschland GmbH
C3  - Lecture Notes in Networks and Systems
T1  - Object Detection and Reinforcement Learning Approach for Intelligent Control of UAV
EP  - 669
SP  - 659
VL  - 472 LNNS
DO  - 10.1007/978-3-031-05230-9_79
ER  - 

@conference{
author = "Miljković, Zoran and Jevtić, Đorđe",
year = "2022",
abstract = "In recent years, the development of deep learning models that can generate more accurate predictions and operate in real-time has brought both opportunities and challenges across the various domains of robotic vision. This breakthrough enables researchers to design and deploy more challenging tasks on intelligent mobile robots, which require emphasized abilities of learning and reasoning. In this paper, a new method for intelligent robot control, based on deep learning and reinforcement learning is proposed. The fundamental idea of this work is how the UAV equipped with a monocular camera can learn significant information about the object of interest in the context of its localization and navigation. For such purpose, the object detection system based on Tiny YOLOv2 architecture is employed. Furthermore, bounding box data generated by a convolution neural network is utilized for depth estimation and determining object boundaries. This information has shown how the state-space dimensions can be significantly reduced, which was essential for further implementation of the Q-learning algorithm. In order to test the proposed framework, a model is developed in MATLAB Simulink. The simulation, which covered different scenarios, was carried out on the UAV within the 3D scene rendered by Unreal Engine. The obtained results have demonstrated the applicability of the proposed methodology for depth estimation, gathering information about the object, object-driven navigation, and autonomous localization and navigation.",
publisher = "Springer Science and Business Media Deutschland GmbH",
journal = "Lecture Notes in Networks and Systems",
title = "Object Detection and Reinforcement Learning Approach for Intelligent Control of UAV",
pages = "669-659",
volume = "472 LNNS",
doi = "10.1007/978-3-031-05230-9_79"
}

Miljković, Z.,& Jevtić, Đ.. (2022). Object Detection and Reinforcement Learning Approach for Intelligent Control of UAV. in Lecture Notes in Networks and Systems
Springer Science and Business Media Deutschland GmbH., 472 LNNS, 659-669.
https://doi.org/10.1007/978-3-031-05230-9_79

Miljković Z, Jevtić Đ. Object Detection and Reinforcement Learning Approach for Intelligent Control of UAV. in Lecture Notes in Networks and Systems. 2022;472 LNNS:659-669.
doi:10.1007/978-3-031-05230-9_79 .

Miljković, Zoran, Jevtić, Đorđe, "Object Detection and Reinforcement Learning Approach for Intelligent Control of UAV" in Lecture Notes in Networks and Systems, 472 LNNS (2022):659-669,
https://doi.org/10.1007/978-3-031-05230-9_79 . .

TY  - CONF
AU  - Miljković, Zoran
AU  - Babić, Bojan
AU  - Petrović, Milica
AU  - Jokić, Aleksandar
AU  - Miljković, Katarina
AU  - Jevtić, Đorđe
AU  - Đokić, Lazar
PY  - 2022
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/3969
AB  - Projekat MISSION4.0 podrazumevao je, u okviru nekoliko radnih paketa, razvoj inteligentnog stereo-vizuelnog upravljanja mobilnih robota, kao i optimalno planiranje i terminiranje tehnoloških procesa, i to baziranim na tehnikama veštačke inteligencije, posebno na konvolucionim veštačkim neuronskim mrežama i biološki inspirisanim algoritmima optimizacije. Tokom dvogodišnjih intenzivnih naučnih istraživanja razvijena je nova metodologija za autonomnu navigaciju i inteligentno upravljanje mobilnih robota sopstvenog razvoja, nazvanih RAICO i DOMINO. Generisanje optimalnog plana terminiranja tehnoloških procesa, u okviru koga se izvršava i inteligentni unutrašnji transport korišćenjem mobilnih robota, takođe je bio jedan od važnih ciljeva ovih naprednih istraživanja. U ovom radu, dat je pregled nekih od ključnih rezultata projekta MISSION4.0, poput publikovanih u vodećim međunarodnim i nacionalnim naučnim časopisima, objavljenih poglavlja u naučnim monografijama, saopštenih i odštampanih naučnih radova u zbornicima prestižnih konferencija održanih u inostranstvu i regionu, zatim u okviru verifikovanih tehničkih rešenja, kao i preko skupova podataka sa otvorenim pristupom.
C3  - 43. JUPITER Konferencija, 39. simpozijum „NU-ROBOTI-FTS“, Zbornik radova
T1  - Inteligentno stereo-vizuelno upravljanje mobilnih robota i optimalno terminiranje tehnoloških procesa - pregled rezultata istraživanja u okviru projekta MISSION4.0/Intelligent stereo-visual mobile robot control and optimal process planning and scheduling – overview of research results within the project MISSION4.0
SP  - 3.13-3.25
UR  - https://hdl.handle.net/21.15107/rcub_machinery_3969
ER  - 

@conference{
author = "Miljković, Zoran and Babić, Bojan and Petrović, Milica and Jokić, Aleksandar and Miljković, Katarina and Jevtić, Đorđe and Đokić, Lazar",
year = "2022",
abstract = "Projekat MISSION4.0 podrazumevao je, u okviru nekoliko radnih paketa, razvoj inteligentnog stereo-vizuelnog upravljanja mobilnih robota, kao i optimalno planiranje i terminiranje tehnoloških procesa, i to baziranim na tehnikama veštačke inteligencije, posebno na konvolucionim veštačkim neuronskim mrežama i biološki inspirisanim algoritmima optimizacije. Tokom dvogodišnjih intenzivnih naučnih istraživanja razvijena je nova metodologija za autonomnu navigaciju i inteligentno upravljanje mobilnih robota sopstvenog razvoja, nazvanih RAICO i DOMINO. Generisanje optimalnog plana terminiranja tehnoloških procesa, u okviru koga se izvršava i inteligentni unutrašnji transport korišćenjem mobilnih robota, takođe je bio jedan od važnih ciljeva ovih naprednih istraživanja. U ovom radu, dat je pregled nekih od ključnih rezultata projekta MISSION4.0, poput publikovanih u vodećim međunarodnim i nacionalnim naučnim časopisima, objavljenih poglavlja u naučnim monografijama, saopštenih i odštampanih naučnih radova u zbornicima prestižnih konferencija održanih u inostranstvu i regionu, zatim u okviru verifikovanih tehničkih rešenja, kao i preko skupova podataka sa otvorenim pristupom.",
journal = "43. JUPITER Konferencija, 39. simpozijum „NU-ROBOTI-FTS“, Zbornik radova",
title = "Inteligentno stereo-vizuelno upravljanje mobilnih robota i optimalno terminiranje tehnoloških procesa - pregled rezultata istraživanja u okviru projekta MISSION4.0/Intelligent stereo-visual mobile robot control and optimal process planning and scheduling – overview of research results within the project MISSION4.0",
pages = "3.13-3.25",
url = "https://hdl.handle.net/21.15107/rcub_machinery_3969"
}

Miljković, Z., Babić, B., Petrović, M., Jokić, A., Miljković, K., Jevtić, Đ.,& Đokić, L.. (2022). Inteligentno stereo-vizuelno upravljanje mobilnih robota i optimalno terminiranje tehnoloških procesa - pregled rezultata istraživanja u okviru projekta MISSION4.0/Intelligent stereo-visual mobile robot control and optimal process planning and scheduling – overview of research results within the project MISSION4.0. in 43. JUPITER Konferencija, 39. simpozijum „NU-ROBOTI-FTS“, Zbornik radova, 3.13-3.25.
https://hdl.handle.net/21.15107/rcub_machinery_3969

Miljković Z, Babić B, Petrović M, Jokić A, Miljković K, Jevtić Đ, Đokić L. Inteligentno stereo-vizuelno upravljanje mobilnih robota i optimalno terminiranje tehnoloških procesa - pregled rezultata istraživanja u okviru projekta MISSION4.0/Intelligent stereo-visual mobile robot control and optimal process planning and scheduling – overview of research results within the project MISSION4.0. in 43. JUPITER Konferencija, 39. simpozijum „NU-ROBOTI-FTS“, Zbornik radova. 2022;:3.13-3.25.
https://hdl.handle.net/21.15107/rcub_machinery_3969 .

Miljković, Zoran, Babić, Bojan, Petrović, Milica, Jokić, Aleksandar, Miljković, Katarina, Jevtić, Đorđe, Đokić, Lazar, "Inteligentno stereo-vizuelno upravljanje mobilnih robota i optimalno terminiranje tehnoloških procesa - pregled rezultata istraživanja u okviru projekta MISSION4.0/Intelligent stereo-visual mobile robot control and optimal process planning and scheduling – overview of research results within the project MISSION4.0" in 43. JUPITER Konferencija, 39. simpozijum „NU-ROBOTI-FTS“, Zbornik radova (2022):3.13-3.25,
https://hdl.handle.net/21.15107/rcub_machinery_3969 .

TY  - GEN
AU  - Miljković, Zoran
AU  - Jevtić, Đorđe
AU  - Svorcan, Jelena
PY  - 2021
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/6625
AB  - Roboti koji imaju mogućnost kretanja uz vertikalnu podlogu (engl. wall-climbing), a u koje spadaju i roboti namenjeni posebnim zadacima kao što je čišćenje gabaritnih staklenih površina eksterijera visokih zgrada (engl. glass and façade-cleaning), predstavljaju predmet brojnih istraživanja u prethodnih trideset godina. Interesovanja naučne i stručne zajednice u ovoj oblasti su posledica pre svega njihovog velikog potencijala za rešavanje mnogobrojnih izazova kao što su održavanje i inspekcija građevinskih konstrukcija, ispitivanja teško dostupnih ili veoma opasnih radnih mesta i dr. Iako je na ovom polju ostvaren vidan napredak poslednjih nekoliko godina, ova tehnologija i dalje poseduje određena ograničenja kao što su nemogućnost kontinualnog kretanja ovih robota po fizički odvojenim površinama visokih zgrada i nemogućnost kretanja po neravnim površinama. Male bespilotne letelice (MBL) predstavljaju aktuelni tip letelica poslednjih dvadeset godina, a koje mogu da se korisno upotrebe u širokom opsegu primena. Minijaturizacija i smanjenje troškova električnih komponenti doveli su do njihove komercijalizacije i masovne upotrebe u mnogim oblastima, kao što su gašenje požara, inspekcija, nadzor, farbanje, održavanje vetro-generatora i brodova. Najveću primenu u praksi pronašli su kvadkopteri, pre svega zbog činjenice da se pomoću četiri veličine, tj. upravljanjem brzinama obrta propelera, može ostvariti šest stepeni slobode pri kretanju. Prednosti ovih letelica su dobre manevarske sposobnosti i jednostavno upravljanje. Međutim, smanjenje njihovih dimenzija dovodi do smanjenja efikasnosti, kao i povećanja viskoznih efekata što je posledica malih Rejnoldsovih brojeva. Koncept predstavljen ovim predavanjem po pozivu podrazumeva sledeće prioritete: 1. Realizovati robotski sistem za čišćenje koji treba da omogući kvalitetno obavljanje ove namene. 2. Ostvariti bezbednu, pouzdanu i laku tranziciju. 3. Osmisliti sistem za prianjanje koji će omogućiti robotu potrebnu mobilnost u svim pravcima pri izrvšavanju zadatka na radnim površinama različitih oblika uz minimalni utrošak energije. 4. Obezbediti robotu mogućnost savladavanja prepreka malih dimenzija radi izbegavanja potrebe za čestom tranzicijom. 5. Ostvariti bezbednost u radu i u slučaju neplaniranog otkaza sistema za prianjanje. 6. Omogućiti bezbedno spuštanje robota na tlo usled otkaza nekog od motora namenjenih generisanju vučne sile. Zadatak koji se postavlja pred mobilni robot letelicu je učenje optimalne putanje od početnog položaja (predstavlja položaj robota u neposrednoj blizini objekta) do ciljnog položaja predstavlja položaj robota na radnoj površini. Određivanje ciljnog položaja se ostvaruje aktiviranjem kamere kao spoljašnjeg senzora koja uz pomoć metoda mašinskog gledanja omogućava mobilnom robotu letelici detektovanje staklenih površina, kao i izdvajanje karakterističnih objekata. Kako je u okviru navedenog problema nemoguće odrediti tačan matematički model kretanja mobilnog robota letelice, odnosno okruženja, uvodi se pojam mašinskog učenja ojačavanjem (engl. Reinforcement Learning). Dva osnovna činioca koncepta mašinskog učenja ojačavanjem predstavljaju inteligentni agent i okruženje. Inteligentni agent ima zadatak da istraživanjem okruženja pomoću eksternih senzora kao i eksploatacijom stečenog znanja generiše optimalno ponašanje u cilju izvršavanja postavljenog tehnološkog zadatka. Stanje sistema se može definisati kao skup komponenti nastalih kao rezultat akcija robota i/ili rezultat interakcije robot okruženje. Stanja mogu činiti sledeći elementi: položaj robota u okruženju u odnosu na izabrani referentni koordinatni sistem, njegova brzina kretanja, položaj i brzina kretanja pokretnih objekata u okruženju i sl. Nagradna oceana stanja (engl. Reward ) se definiše kao stepen uspešnosti odabrane akcije u prethodnom stanju sistema izražene u vidu numeričke vrednosti. Cilj agenta jeste da pronađe skup najpovoljnijih akcija u svim stanjima mobilnog robota letelice pri njenom kretanju od početnog do ciljnog položaja. Na osnovu informacija o trenutnom stanju sistema kao i trenutnom stepenu obučenosti, inteligentni agent treba da odabere akciju koja će ga dovesti u naredni položaj. Ovaj položaj predstavlja ulaz u upravljačku jedinicu za kontrolu položaja koja treba da odredi signale na ulazu u kontrolere rada električnih motora kako bi se generisale odgovarajuće vučne sile. Stanje sistema u razmatranom primeru predstavlja položaj mobilnog robota letelice u režimu lebdenja. Okruženje je sastavljeno od sfera jednakih prečnika, čiji su centri moguća stanja sistema. U konkretnom primeru razmatrani prostor je dimenzija 9000x6000x4000mm, i
PB  - Mašinski fakultet Univerziteta u Beogradu
T2  - 7. Kongres studenata tehnike - "TEHNOLOGIJE MODERNOG INŽENjERSTVA"
T1  - AUTONOMNOST KRETANjA MOBILNOG ROBOTA -LETELICE ZA RAD NA VISINAMA – SPECIFIČNOSTI KONFIGURACIJE, MODELIRANjE, FUNKCIONALNA APROKSIMACIJA I MAŠINSKO UČENjE OJAČAVANjEM
UR  - https://hdl.handle.net/21.15107/rcub_machinery_6625
ER  - 

@misc{
author = "Miljković, Zoran and Jevtić, Đorđe and Svorcan, Jelena",
year = "2021",
abstract = "Roboti koji imaju mogućnost kretanja uz vertikalnu podlogu (engl. wall-climbing), a u koje spadaju i roboti namenjeni posebnim zadacima kao što je čišćenje gabaritnih staklenih površina eksterijera visokih zgrada (engl. glass and façade-cleaning), predstavljaju predmet brojnih istraživanja u prethodnih trideset godina. Interesovanja naučne i stručne zajednice u ovoj oblasti su posledica pre svega njihovog velikog potencijala za rešavanje mnogobrojnih izazova kao što su održavanje i inspekcija građevinskih konstrukcija, ispitivanja teško dostupnih ili veoma opasnih radnih mesta i dr. Iako je na ovom polju ostvaren vidan napredak poslednjih nekoliko godina, ova tehnologija i dalje poseduje određena ograničenja kao što su nemogućnost kontinualnog kretanja ovih robota po fizički odvojenim površinama visokih zgrada i nemogućnost kretanja po neravnim površinama. Male bespilotne letelice (MBL) predstavljaju aktuelni tip letelica poslednjih dvadeset godina, a koje mogu da se korisno upotrebe u širokom opsegu primena. Minijaturizacija i smanjenje troškova električnih komponenti doveli su do njihove komercijalizacije i masovne upotrebe u mnogim oblastima, kao što su gašenje požara, inspekcija, nadzor, farbanje, održavanje vetro-generatora i brodova. Najveću primenu u praksi pronašli su kvadkopteri, pre svega zbog činjenice da se pomoću četiri veličine, tj. upravljanjem brzinama obrta propelera, može ostvariti šest stepeni slobode pri kretanju. Prednosti ovih letelica su dobre manevarske sposobnosti i jednostavno upravljanje. Međutim, smanjenje njihovih dimenzija dovodi do smanjenja efikasnosti, kao i povećanja viskoznih efekata što je posledica malih Rejnoldsovih brojeva. Koncept predstavljen ovim predavanjem po pozivu podrazumeva sledeće prioritete: 1. Realizovati robotski sistem za čišćenje koji treba da omogući kvalitetno obavljanje ove namene. 2. Ostvariti bezbednu, pouzdanu i laku tranziciju. 3. Osmisliti sistem za prianjanje koji će omogućiti robotu potrebnu mobilnost u svim pravcima pri izrvšavanju zadatka na radnim površinama različitih oblika uz minimalni utrošak energije. 4. Obezbediti robotu mogućnost savladavanja prepreka malih dimenzija radi izbegavanja potrebe za čestom tranzicijom. 5. Ostvariti bezbednost u radu i u slučaju neplaniranog otkaza sistema za prianjanje. 6. Omogućiti bezbedno spuštanje robota na tlo usled otkaza nekog od motora namenjenih generisanju vučne sile. Zadatak koji se postavlja pred mobilni robot letelicu je učenje optimalne putanje od početnog položaja (predstavlja položaj robota u neposrednoj blizini objekta) do ciljnog položaja predstavlja položaj robota na radnoj površini. Određivanje ciljnog položaja se ostvaruje aktiviranjem kamere kao spoljašnjeg senzora koja uz pomoć metoda mašinskog gledanja omogućava mobilnom robotu letelici detektovanje staklenih površina, kao i izdvajanje karakterističnih objekata. Kako je u okviru navedenog problema nemoguće odrediti tačan matematički model kretanja mobilnog robota letelice, odnosno okruženja, uvodi se pojam mašinskog učenja ojačavanjem (engl. Reinforcement Learning). Dva osnovna činioca koncepta mašinskog učenja ojačavanjem predstavljaju inteligentni agent i okruženje. Inteligentni agent ima zadatak da istraživanjem okruženja pomoću eksternih senzora kao i eksploatacijom stečenog znanja generiše optimalno ponašanje u cilju izvršavanja postavljenog tehnološkog zadatka. Stanje sistema se može definisati kao skup komponenti nastalih kao rezultat akcija robota i/ili rezultat interakcije robot okruženje. Stanja mogu činiti sledeći elementi: položaj robota u okruženju u odnosu na izabrani referentni koordinatni sistem, njegova brzina kretanja, položaj i brzina kretanja pokretnih objekata u okruženju i sl. Nagradna oceana stanja (engl. Reward ) se definiše kao stepen uspešnosti odabrane akcije u prethodnom stanju sistema izražene u vidu numeričke vrednosti. Cilj agenta jeste da pronađe skup najpovoljnijih akcija u svim stanjima mobilnog robota letelice pri njenom kretanju od početnog do ciljnog položaja. Na osnovu informacija o trenutnom stanju sistema kao i trenutnom stepenu obučenosti, inteligentni agent treba da odabere akciju koja će ga dovesti u naredni položaj. Ovaj položaj predstavlja ulaz u upravljačku jedinicu za kontrolu položaja koja treba da odredi signale na ulazu u kontrolere rada električnih motora kako bi se generisale odgovarajuće vučne sile. Stanje sistema u razmatranom primeru predstavlja položaj mobilnog robota letelice u režimu lebdenja. Okruženje je sastavljeno od sfera jednakih prečnika, čiji su centri moguća stanja sistema. U konkretnom primeru razmatrani prostor je dimenzija 9000x6000x4000mm, i",
publisher = "Mašinski fakultet Univerziteta u Beogradu",
journal = "7. Kongres studenata tehnike - "TEHNOLOGIJE MODERNOG INŽENjERSTVA"",
title = "AUTONOMNOST KRETANjA MOBILNOG ROBOTA -LETELICE ZA RAD NA VISINAMA – SPECIFIČNOSTI KONFIGURACIJE, MODELIRANjE, FUNKCIONALNA APROKSIMACIJA I MAŠINSKO UČENjE OJAČAVANjEM",
url = "https://hdl.handle.net/21.15107/rcub_machinery_6625"
}

Miljković, Z., Jevtić, Đ.,& Svorcan, J.. (2021). AUTONOMNOST KRETANjA MOBILNOG ROBOTA -LETELICE ZA RAD NA VISINAMA – SPECIFIČNOSTI KONFIGURACIJE, MODELIRANjE, FUNKCIONALNA APROKSIMACIJA I MAŠINSKO UČENjE OJAČAVANjEM. in 7. Kongres studenata tehnike - "TEHNOLOGIJE MODERNOG INŽENjERSTVA"
Mašinski fakultet Univerziteta u Beogradu..
https://hdl.handle.net/21.15107/rcub_machinery_6625

Miljković Z, Jevtić Đ, Svorcan J. AUTONOMNOST KRETANjA MOBILNOG ROBOTA -LETELICE ZA RAD NA VISINAMA – SPECIFIČNOSTI KONFIGURACIJE, MODELIRANjE, FUNKCIONALNA APROKSIMACIJA I MAŠINSKO UČENjE OJAČAVANjEM. in 7. Kongres studenata tehnike - "TEHNOLOGIJE MODERNOG INŽENjERSTVA". 2021;.
https://hdl.handle.net/21.15107/rcub_machinery_6625 .

Miljković, Zoran, Jevtić, Đorđe, Svorcan, Jelena, "AUTONOMNOST KRETANjA MOBILNOG ROBOTA -LETELICE ZA RAD NA VISINAMA – SPECIFIČNOSTI KONFIGURACIJE, MODELIRANjE, FUNKCIONALNA APROKSIMACIJA I MAŠINSKO UČENjE OJAČAVANjEM" in 7. Kongres studenata tehnike - "TEHNOLOGIJE MODERNOG INŽENjERSTVA" (2021),
https://hdl.handle.net/21.15107/rcub_machinery_6625 .

TY  - CONF
AU  - Jevtić, Đorđe
AU  - Svorcan, Jelena
AU  - Radulović, Radoslav
PY  - 2021
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/3647
AB  - In recent years, quadrotors are one of the most popular platforms for the development of unmanned aerial vehicles, and their application trend is rapidly increasing for both commercial and research purposes. Their main advantages compared to other types of flying vehicles are the ability to hover, minimal operating space, vertical take-off, and landing capability, as well as smaller overall dimensions. However, their breakthrough into the market is due to their longer flight time and the fact that today they can carry much more payload. This paper aims to present the basic idea behind the conceptual development of the quadrotor, with special reference to aerodynamic effects that are important for this type of aircraft. It will be shown that, although thrust force is represented by simplified equations in literature, in the general case it depends on the vehicular velocity and its angle of attack. Therefore, its expressions will be different and will depend on flight mode, as is shown in the paper. Furthermore, it will be presented that less power is needed for the same thrust force when the quadrotor flights near the ground. The main advantages of the quadrotor concept will be explained, where it will be shown that blade flapping and the gyroscopic effect can be significantly suppressed due to the opposite direction of rotation of the rotor. The kinematic model is given and the formulated dynamic model is based on Newton-Euler formalism.
PB  - Springer Science and Business Media Deutschland GmbH
C3  - Lecture Notes in Networks and Systems
T1  - Flight Mechanics, Aerodynamics and Modelling of Quadrotor
EP  - 689
SP  - 681
VL  - 233
DO  - 10.1007/978-3-030-75275-0_75
ER  - 

@conference{
author = "Jevtić, Đorđe and Svorcan, Jelena and Radulović, Radoslav",
year = "2021",
abstract = "In recent years, quadrotors are one of the most popular platforms for the development of unmanned aerial vehicles, and their application trend is rapidly increasing for both commercial and research purposes. Their main advantages compared to other types of flying vehicles are the ability to hover, minimal operating space, vertical take-off, and landing capability, as well as smaller overall dimensions. However, their breakthrough into the market is due to their longer flight time and the fact that today they can carry much more payload. This paper aims to present the basic idea behind the conceptual development of the quadrotor, with special reference to aerodynamic effects that are important for this type of aircraft. It will be shown that, although thrust force is represented by simplified equations in literature, in the general case it depends on the vehicular velocity and its angle of attack. Therefore, its expressions will be different and will depend on flight mode, as is shown in the paper. Furthermore, it will be presented that less power is needed for the same thrust force when the quadrotor flights near the ground. The main advantages of the quadrotor concept will be explained, where it will be shown that blade flapping and the gyroscopic effect can be significantly suppressed due to the opposite direction of rotation of the rotor. The kinematic model is given and the formulated dynamic model is based on Newton-Euler formalism.",
publisher = "Springer Science and Business Media Deutschland GmbH",
journal = "Lecture Notes in Networks and Systems",
title = "Flight Mechanics, Aerodynamics and Modelling of Quadrotor",
pages = "689-681",
volume = "233",
doi = "10.1007/978-3-030-75275-0_75"
}

Jevtić, Đ., Svorcan, J.,& Radulović, R.. (2021). Flight Mechanics, Aerodynamics and Modelling of Quadrotor. in Lecture Notes in Networks and Systems
Springer Science and Business Media Deutschland GmbH., 233, 681-689.
https://doi.org/10.1007/978-3-030-75275-0_75

Jevtić Đ, Svorcan J, Radulović R. Flight Mechanics, Aerodynamics and Modelling of Quadrotor. in Lecture Notes in Networks and Systems. 2021;233:681-689.
doi:10.1007/978-3-030-75275-0_75 .

Jevtić, Đorđe, Svorcan, Jelena, Radulović, Radoslav, "Flight Mechanics, Aerodynamics and Modelling of Quadrotor" in Lecture Notes in Networks and Systems, 233 (2021):681-689,
https://doi.org/10.1007/978-3-030-75275-0_75 . .

TY  - CONF
AU  - Miljković, Zoran
AU  - Jevtić, Đorđe
AU  - Svorcan, Jelena
PY  - 2021
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/4625
AB  - In the last two decades, the rapid development of unmanned aerial vehicles (UAVs) resulted in their usage for a wide range of applications. Miniaturization and cost reduction of electrical components have led to their commercialization, and today they can be utilized for various tasks in an unknown environment. Finding the optimal path based on the start and target pose information is one of the most complex demands for any intelligent UAV system. As this problem requires a high level of adaptability and learning capability of the UAV, the framework based
on reinforcement learning is proposed for the localization and navigation tasks. In this paper, Q-learning algorithm for the autonomous navigation of the UAV in 3D space is implemented. To test the proposed methodology for UAV intelligent control, the simulation is conducted in ROS-Gazebo environment. The obtained simulation results have shown that the UAV can reach the target pose autonomously in an efficient way.
PB  - Novi Sad : Faculty of Technical Sciences
C3  - Proceedings of the 14th International Scientific Conference MMA 2021 – Flexible Technologies, Novi Sad, September 23-25, 2021
T1  - Reinforcement Learning Approach for Autonomous UAV Navigation in 3D Space
EP  - 192
SP  - 189
SP  - 
UR  - https://hdl.handle.net/21.15107/rcub_machinery_4625
ER  - 

@conference{
author = "Miljković, Zoran and Jevtić, Đorđe and Svorcan, Jelena",
year = "2021",
abstract = "In the last two decades, the rapid development of unmanned aerial vehicles (UAVs) resulted in their usage for a wide range of applications. Miniaturization and cost reduction of electrical components have led to their commercialization, and today they can be utilized for various tasks in an unknown environment. Finding the optimal path based on the start and target pose information is one of the most complex demands for any intelligent UAV system. As this problem requires a high level of adaptability and learning capability of the UAV, the framework based
on reinforcement learning is proposed for the localization and navigation tasks. In this paper, Q-learning algorithm for the autonomous navigation of the UAV in 3D space is implemented. To test the proposed methodology for UAV intelligent control, the simulation is conducted in ROS-Gazebo environment. The obtained simulation results have shown that the UAV can reach the target pose autonomously in an efficient way.",
publisher = "Novi Sad : Faculty of Technical Sciences",
journal = "Proceedings of the 14th International Scientific Conference MMA 2021 – Flexible Technologies, Novi Sad, September 23-25, 2021",
title = "Reinforcement Learning Approach for Autonomous UAV Navigation in 3D Space",
pages = "192-189-",
url = "https://hdl.handle.net/21.15107/rcub_machinery_4625"
}

Miljković, Z., Jevtić, Đ.,& Svorcan, J.. (2021). Reinforcement Learning Approach for Autonomous UAV Navigation in 3D Space. in Proceedings of the 14th International Scientific Conference MMA 2021 – Flexible Technologies, Novi Sad, September 23-25, 2021
Novi Sad : Faculty of Technical Sciences., 189-192.
https://hdl.handle.net/21.15107/rcub_machinery_4625

Miljković Z, Jevtić Đ, Svorcan J. Reinforcement Learning Approach for Autonomous UAV Navigation in 3D Space. in Proceedings of the 14th International Scientific Conference MMA 2021 – Flexible Technologies, Novi Sad, September 23-25, 2021. 2021;:189-192.
https://hdl.handle.net/21.15107/rcub_machinery_4625 .

Miljković, Zoran, Jevtić, Đorđe, Svorcan, Jelena, "Reinforcement Learning Approach for Autonomous UAV Navigation in 3D Space" in Proceedings of the 14th International Scientific Conference MMA 2021 – Flexible Technologies, Novi Sad, September 23-25, 2021 (2021):189-192,
https://hdl.handle.net/21.15107/rcub_machinery_4625 .