Naslov
Simulation of robotic learning in assembly process

Autori
Jerbić, Bojan ; Grolinger, Katarina ; Vranješ, Božo

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 7th International DAAAM Symposium / Katalinić, Branko - Beč : DAAAM International Vienna, 1996, 185-186

Skup
Product & Manufacturing: Flexibility, Integration, Intelligence

Mjesto i datum
Beč, Austrija, 17.10.1996. - 19.10.1996

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
intelligent planning; learning; mobile robots; automatic assembly

Sažetak
Intelligent robot behavior in assembly processes is a fundamental issue in the development of intelligent and flexible assembly systems. Intelligent robot behavior comprises the robot's capability to act in unpredictable and chaotic situations, which require not just a change but the innovation of the robot's working actions. Planning of intelligent robot behavior addresses three main issues: finding task solutions in unknown situations, learning from experience and recognizing the similarity of problem paradigms. The paper presents a planning system which integrates the reinforcement learning method and a neural network approach with the aim to ensure autonomous robot behavior in unpredictable working conditions. The intelligent planning system is simulated using object-oriented techniques and verified on planned and random examples, proving the main advantages of the proposed approach: autonomous learning, which is invariant with regard to the order of training samples, and enables single iteration learning progress.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo

POVEZANOST RADA