Comparative Analysis of Arm Control Performance Using Computational Intelligence

Several models of computational intelligence have been proven to be useful in robotic devices control. This work evaluates three models to solve the inverse kinematics problem of a robotic manipulator with two degrees of freedom, which is used to position objects in conjunction with the CoroBot platform. They were initially developed the direct and inverse kinematic models using the homogeneous transformation matrices, extracting from these, the training, testing and validation data used in the three models. This paper takes advantage of the great potential of artificial neural networks, in order to determine the feasibility and response of the experiments performed, keeping in focus the possible applications and modification of design and training parameters. The models used are Feedforward Neural Networks, Neuro-Fuzzy Systems and finally Echo State Networks.

[1]  Tianyou Chai,et al.  Neural-Network-Based Contouring Control for Robotic Manipulators in Operational Space , 2012, IEEE Transactions on Control Systems Technology.

[2]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[3]  H. Jaeger,et al.  Reservoir riddles: suggestions for echo state network research , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[4]  Kourosh Kiani,et al.  Inverse Kinematics solution of PUMA 560 robot arm using ANFIS , 2011, 2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI).

[5]  Lei Liu,et al.  Predictive Control of Vehicle Based on Echo State Network , 2011, 2011 International Conference on Intelligence Science and Information Engineering.

[6]  Li-xin Wei,et al.  A new solution for inverse kinematics of manipulator based on neural network , 2003, Proceedings of the 2003 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.03EX693).

[7]  Prithviraj Dasgupta,et al.  Multi-agent Coalition Formation for Distributed Area Coverage: Analysis and Evaluation , 2010, 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.

[8]  Herbert G. Tanner,et al.  Spatially distributed cellular neural networks , 2011, Int. J. Intell. Comput. Cybern..

[9]  Dipak M. Adhyaru,et al.  Adaptive Neuro-Fuzzy Inference System based control of robotic manipulators , 2010, 2010 International Conference on Mechanical and Electrical Technology.

[10]  D.T. Pham,et al.  Learning the inverse kinematics of a robot manipulator using the Bees Algorithm , 2008, 2008 6th IEEE International Conference on Industrial Informatics.

[11]  Bertrand Tondu,et al.  Kinematic modelling of anthropomorphic robot upper limb with human-like hands , 2009, 2009 International Conference on Advanced Robotics.

[12]  Min Han,et al.  Analyzing the state space property of echo state networks for chaotic system prediction , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[13]  Frank L. Lewis,et al.  Intelligent optimal control of robotic manipulators using neural networks , 2000, Autom..

[14]  Ganesh K. Venayagamoorthy,et al.  Effects of spectral radius and settling time in the performance of echo state networks , 2009, Neural Networks.

[15]  Xinqian Bian,et al.  Identification of non-linear dynamic model of UUV based on ESN neural network , 2011, Proceedings of the 30th Chinese Control Conference.