Unconstrained evolutionary and gradient descent-based tuning of fuzzy-partitions for UAV dynamic modeling

In this paper, a novel fuzzy identification method for dynamic modelling of quadrotors UAV is presented. The method is based on a special parameterization of the antecedent part of fuzzy systems that results in fuzzy-partitions for antecedents. This antecedent parameter representation method of fuzzy rules ensures upholding of predefined linguistic value ordering and ensures that fuzzy-partitions remain intact throughout an unconstrained hybrid evolutionary and gradient descent based optimization process. In the equations of motion the first order derivative component is calculated based on Christoffel symbols, the derivatives of fuzzy systems are used for modelling the Coriolis effects, gyroscopic and centrifugal terms. The non-linear parameters are subjected to an initial global evolutionary optimization scheme and fine tuning with gradient descent based local search. Simulation results of the proposed new quadrotor dynamic model identification method are promising.

[1]  Naoyuki Kubota,et al.  Bacterial memetic algorithm for offline path planning of mobile robots , 2012, Memetic Comput..

[2]  Li-Xin Wang,et al.  Adaptive fuzzy systems and control - design and stability analysis , 1994 .

[3]  David L. Darmofal,et al.  Unmanned Aerial Vehicles , 2016, Encyclopedia of GIS.

[4]  Ivan Stojkovic,et al.  Qualitative Evaluation of Flight Controller Performances for Autonomous Quadrotors , 2013 .

[5]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[6]  Gyula Mester.  Adaptive force and position control of rigid-link flexible-joint SCARA robots , 1994, Proceedings of IECON'94 - 20th Annual Conference of IEEE Industrial Electronics.

[7]  Amir Mosavi,et al.  Learning in Robotics , 2017 .

[8]  Gyula Mester,et al.  The Modeling and Simulation of an Autonomous Quad-Rotor Microcopter in a Virtual Outdoor Scenario , 2011 .

[9]  Kalyanmoy Deb,et al.  Muiltiobjective Optimization Using Nondominated Sorting in Genetic Algorithms , 1994, Evolutionary Computation.

[10]  Chuen-Tsai Sun,et al.  Neuro-fuzzy And Soft Computing: A Computational Approach To Learning And Machine Intelligence [Books in Brief] , 1997, IEEE Transactions on Neural Networks.

[11]  Goldberg,et al.  Genetic algorithms , 1993, Robust Control Systems with Genetic Algorithms.

[12]  G. Mester.  Intelligent Mobile Robot Controller Design , 2006, 2006 International Conference on Intelligent Engineering Systems.

[13]  David E. Goldberg,et al.  Genetic Algorithms: A Bibliography , 1997 .

[14]  László T. Kóczy,et al.  Hierarchical fuzzy system modeling by Genetic and Bacterial Programming approaches , 2010, International Conference on Fuzzy Systems.

[15]  Josip Kasac,et al.  A computational approach to parameter identification of spatially distributed nonlinear systems with unknown initial conditions , 2014, 2014 IEEE Symposium on Robotic Intelligence in Informationally Structured Space (RiiSS).

[16]  László T. Kóczy,et al.  Comparative Investigation of Various Evolutionary and Memetic Algorithms , 2010 .

[17]  Dimiter Driankov,et al.  Fuzzy model identification - selected approaches , 1997 .

[18]  A. Rodic,et al.  Modeling and simulation of quad-rotor dynamics and spatial navigation , 2011, 2011 IEEE 9th International Symposium on Intelligent Systems and Informatics.

[19]  Gyula Mester,et al.  Modeling of Autonomous Hexa-Rotor Microcopter , 2015 .

[20]  Josip Kasać,et al.  Robust tracking control of a quadrotor helicopter without velocity measurement , 2012 .

[21]  Dimiter Driankov,et al.  Fuzzy Model Identification , 1997, Springer Berlin Heidelberg.