Creating a CMAC with overlapping basis functions in order to prevent weight drift
- 162 Downloads
The cerebellar model articulation controller, or CMAC, is a type of associative memory neural network suitable for use in direct adaptive control schemes. However, the CMAC exhibits a large trade-off between stability and performance when inputs oscillate. This is due to the local nature of the basis functions—an input oscillating between two basis functions on one layer can cause their weights to drift in opposite directions. Continued drift will eventually affect performance, resulting in bursting. The proposed method overlaps the basis functions on each layer so that an oscillation will occur within basis functions. This makes the weights much less prone to drift. A simulation with a flexible joint demonstrates that both high performance and stability can be achieved using the proposed method.
KeywordsCerebellar model articulation controller Direct adaptive control Weight drift Bursting Lyapunov stability Flexible joint
Compliance with ethical standards
Conflict of interest
C.J.B. Macnab declares that he has no conflict of interest.
Human and animal rights
This article does not contain any studies with human participants or animals performed by any of the authors.
- Huang YW, Juang JG (2014) Twin rotor system control based on self-organizing CMAC. In: International conference on machine learning and cybernetics, pp 876–882, LanzhouGoogle Scholar
- Kraft L, Pallotta J (2000) Real-time vibration control using CMAC neural networks with weightsmoothing. In: Proceedings of IEEE American control conference, pp 3939–3943. ChicagoGoogle Scholar
- Lewis F, Jagannathan S, Yesildirek A (1999) Neural network control of robot manipulators and nonlinear systems. Taylor and Francis, PhilidelphiaGoogle Scholar
- Shiev K, Ahmed S, Shakev N, Topalov AV (2016) Trajectory control of manipulators using an adaptive parametric type-2 fuzzy cmac friction and disturbance compensator. In: Hadjiski M, Kasabov N, Filev D, Jotsov V (eds) Novel applications of intelligent systems, studies in computational intelligence. Springer, New York, pp 63–82CrossRefGoogle Scholar
- Taoa T, Su SF (2011) CMAC-based previous step supervisory control schemes for relaxing bound in adaptive fuzzy control. Appl Soft Comput 11(8):57155723Google Scholar
- Wang SY, Tseng CL, Tseng CH, Chou JH, Tsai MH (2013) Design and implementation of adaptive fuzzy cerebellar model articulation controller for direct torque control system. Appl Mech Mater 300–301:1444–1447Google Scholar
- Wu TF, Huang HC, Tsai PS, Hu NT, Yang ZQ (2014) Adaptive fuzzy cmac design for an omni-directional mobile robot. In: International conference on intelligent information hiding and multimedia signal processing, pp 839–843. KitakyushuGoogle Scholar
- Yeh MF, Lu HC (2008) On-line learning CMAC control system. In: International conference on intelligent engineering systems, pp 115–120. MiamiGoogle Scholar
- Yuan Y, Gu W, Yu J (2004) Online learning CMAC neural network control scheme for nonlinear systems. Lecture notes in computer science. In: Yin F, Wang J, Guo C (eds) Advanced neural network. Springer, Berlin, pp 117–122Google Scholar