Hierarchical intelligent control of a learning robot using a camera and system of artificial neural networks

• Autorzy: Miljković Z.
• Języki publikacji: EN

Abstrakty

EN

This paper presents interaction of mechatronic subsystems in order to achieve an adaptive behavior of learning robots. A learning robot is able to deal flexibly with changes in its environment and to execute intelligent tasks. The control strategy for the learning robot is established by using a recognition system and machine learning. The recognition system that utilizes artificial intelligence techniques is used in order to test and verify the hypothesis that learning robots can achieve sensor-actuator co-ordination and team successfully. The hypothesis is tested and verified on the basis of visual information obtained from the camera and an artificial neural network system. For this purpose the experimental set of software packages Make it, ART-1 Simulator and BPNET, as well as the physical model of anthropomorphic mobile robot Don Kihot with four degrees of freedom, are realized.

Słowa kluczowe

EN

hierarchical intelligent robot control; learning robots; recognition system; ART-1 neural network; backpropagation neural network

PL

sterowanie hierarchiczne; robot uczący się; system rozpoznawczy; sieci neuronowe; ART-1; propagacja wsteczna

• Wydawca: Wydawnictwo Politechniki Łódzkiej
• Czasopismo: Journal of Applied Computer Science
• Rocznik: 2000
• Tom: Vol. 8, nr 2
• Strony: 79--97
• Opis fizyczny: Bibliogr. 10 poz.

Twórcy

autor

Miljković Z.

• The University of Belgrade, Mechanical Engineering Faculty, Departament of Production Engineering, 27. Marta 80, 11000 Belgrade, Yugoslavia,

Bibliografia

• [1] Chen, B., Hoberock, L. L., Machine Vision Recognition of Fuzzy Objects Using a New Fuzzy Neural Network, Proc. IEEE Inti. Conf. on Robotics and Automation, Vol. 2, 19%, pp. 1596-1601.
• [2] Dagli,C.H., Artificial Neural Networks for Intelligent Manufacturing, Chapman & Hall, 1994.
• [3] Fukuda,T.,Shibata,T., Theory and Applications of Neural Networks for Industrial Control Systems, IEEE Transactions on Industrial Electronics, Vol. 39, No. 6, 1992, pp. 472489.
• [4] Hashimoto,H.,Kubota,T.,Sato,M.,Harashima,F., Visual Control of Robotic Manipulator Based on Neural Networks, IEEE Transactions on Industrial Electronics,Vol.39,No.6, 1992 pp. 490-4%.
• [5] Miljkovic, Z., Application of ART-1 Neural Network for Pattern Recognition in Robotics, Proc. Inti. Conf. on Communications, Signals & Systems, Vol.l., Bmo- Czech Rep., 19%, pp. 235-238.
• [6] Miljkovic, Z.,Lazarević, I., “ART-1 Simulator” for Identification of Objects in Robotics, Proceedings of the International A.M.S.E Conference on Contribution of Cognition to Modelling-CCM’98, Lyon-Villeurbanne, France, July 1998, pp.5.48-5.51.
• [7] Miljkovic, Z., Lazarevic, I., Control Strategy for Learning Industrial Robot Based on Artificial Neural Network System, Proceedings of the International Conference on Systems, Signals, Control, Computers - SSCC’98, Vol.3, Durban-South Africa, September 1998, pp.124-128.
• [8] Miljkovic, Z., Application of the Recognition System in Industrial Robot Control, Proceedings of the 26rt JUPITER Conference with foreign participants - 22'I‘, Symposium NC * ROBOTS * FMS, Belgrade-Yugoslavia, February 2000, pp.3.21-3.26.
• [9] Sha, D., Bajić, V. В., Adaptive on-line ANN learning algorithm and application to identification of non-linear systems, Informatica: An International journal of Computing and Informatics, Vol. 23, No. 4, 1999, pp. 251-259.
• [10] Visual Basic 5.0, Enterprise edition, Microsoft Corporation, 1997.