Intelligent Control of Industrial Robot Using Recognition System and Artificial Neural Nets
No Thumbnail
Conference object (Published version)
,
Prof. Ilija Ćosić
Metadata
Show full item recordAbstract
This paper presents the hierarchical intelligent control of an industrial robot using a system of artificial neural networks, based on an empirical control strategy. This type of intelligent industrial robots control provides a much wider domain of autonomy in the execution of manufacturing tasks, especially manipulation of parts, so these robots have the ability of machine learning based on "own experience". Conducted research has shown that improvements in terms of programming, flexibility, efficiency and skill of an intelligent mechatronic system - industrial robot depend on the degree of development and implementation of its machine learning by using two artificial neural networks: ART-1 net for pattern recognition of object and four-layer "back-propagation" net for coordinate mapping between the CCD camera and robot coordinates of TCP.
Keywords:
Autonomous industrial robot / ART-1 artificial neural network / Back-propagation artificial neural network / Recognition system / CCD camera / Manipulation robotic task / Machine learning / Hierarchical intelligent robot controlSource:
Proceedings of the 10th International Conference on Industrial Systems - Production systems design, robotics, automation and mechatronics, 1996, I, 229-234Publisher:
- FACULTY OF TECHNICAL SCIENCES, Institute of Industrial Systems Engineering
Collections
Institution/Community
Mašinski fakultetTY - CONF AU - Miljković, Zoran PY - 1996 UR - https://worldcat.org/title/248307832 UR - https://machinery.mas.bg.ac.rs/handle/123456789/5134 AB - This paper presents the hierarchical intelligent control of an industrial robot using a system of artificial neural networks, based on an empirical control strategy. This type of intelligent industrial robots control provides a much wider domain of autonomy in the execution of manufacturing tasks, especially manipulation of parts, so these robots have the ability of machine learning based on "own experience". Conducted research has shown that improvements in terms of programming, flexibility, efficiency and skill of an intelligent mechatronic system - industrial robot depend on the degree of development and implementation of its machine learning by using two artificial neural networks: ART-1 net for pattern recognition of object and four-layer "back-propagation" net for coordinate mapping between the CCD camera and robot coordinates of TCP. PB - FACULTY OF TECHNICAL SCIENCES, Institute of Industrial Systems Engineering C3 - Proceedings of the 10th International Conference on Industrial Systems - Production systems design, robotics, automation and mechatronics T1 - Intelligent Control of Industrial Robot Using Recognition System and Artificial Neural Nets EP - 234 SP - 229 VL - I UR - https://hdl.handle.net/21.15107/rcub_machinery_5134 ER -
@conference{ author = "Miljković, Zoran", year = "1996", abstract = "This paper presents the hierarchical intelligent control of an industrial robot using a system of artificial neural networks, based on an empirical control strategy. This type of intelligent industrial robots control provides a much wider domain of autonomy in the execution of manufacturing tasks, especially manipulation of parts, so these robots have the ability of machine learning based on "own experience". Conducted research has shown that improvements in terms of programming, flexibility, efficiency and skill of an intelligent mechatronic system - industrial robot depend on the degree of development and implementation of its machine learning by using two artificial neural networks: ART-1 net for pattern recognition of object and four-layer "back-propagation" net for coordinate mapping between the CCD camera and robot coordinates of TCP.", publisher = "FACULTY OF TECHNICAL SCIENCES, Institute of Industrial Systems Engineering", journal = "Proceedings of the 10th International Conference on Industrial Systems - Production systems design, robotics, automation and mechatronics", title = "Intelligent Control of Industrial Robot Using Recognition System and Artificial Neural Nets", pages = "234-229", volume = "I", url = "https://hdl.handle.net/21.15107/rcub_machinery_5134" }
Miljković, Z.. (1996). Intelligent Control of Industrial Robot Using Recognition System and Artificial Neural Nets. in Proceedings of the 10th International Conference on Industrial Systems - Production systems design, robotics, automation and mechatronics FACULTY OF TECHNICAL SCIENCES, Institute of Industrial Systems Engineering., I, 229-234. https://hdl.handle.net/21.15107/rcub_machinery_5134
Miljković Z. Intelligent Control of Industrial Robot Using Recognition System and Artificial Neural Nets. in Proceedings of the 10th International Conference on Industrial Systems - Production systems design, robotics, automation and mechatronics. 1996;I:229-234. https://hdl.handle.net/21.15107/rcub_machinery_5134 .
Miljković, Zoran, "Intelligent Control of Industrial Robot Using Recognition System and Artificial Neural Nets" in Proceedings of the 10th International Conference on Industrial Systems - Production systems design, robotics, automation and mechatronics, I (1996):229-234, https://hdl.handle.net/21.15107/rcub_machinery_5134 .