Hardware-in-the-loop architecture with MATLAB/Simulink and QuaRC for rapid prototyping of CMAC neural network controller for ball-and-beam plant

Shatri, Vjosa; Kurtaj, Lavdim; Limani, Ilir

doi:10.23919/mipro.2017.7973606

Cited by 3 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These weights are not adjusted any more, since other circumstances with higher speed are less informative regarding this term. Resulting receptive fields from granule cell-Golgi cell block GrC-GoC_Gx are common unmodulated ones, since modulating signal is tied to constant, as in standard CMAC model [42,28]. During second phase cycling was speeded up to 10 s/cycle, and only inertial and friction terms were adapted.…”

Section: Cmacgbs With Two-phase Learning As Robot Controller and Genementioning

confidence: 99%

Cerebellar Model Controller with new Model of Granule Cell-golgi Cell Building Blocks and Two-phase Learning Acquires Multitude of Generalization Capabilities in Controlling Robot Joint without Exponential Growth in Complexity

Kurtaj¹,

Shatri²,

Limani³

2018

IJECE

Self Cite

View full text Add to dashboard Cite

Processing in the cerebellum is roughly described as feed forward processing of incoming information over three layers of the cerebellar cortex that send intermediate output to deep cerebellar nuclei, the only output from the cerebellum. Beside this main picture there are several feedback routes, mainly not included in models. In this paper we use new model for neuronal circuit of the cerebellar granule cell layer, as collection of idealized granule cell–golgi cell building blocks with capability of generating multi-dimensional receptive fields modulated by separate input coming to lower dendrite tree of Golgi cell. Resulting cerebellar model controller with two-phase learning will acquire multitude of generalization capabilities when used as robot joint controller. This will usually require more than one Purkinje cell per output. Functionality of granule cell-Golgi cell building block was evaluated with simulations using Simulink single compartment spiking neuronal model. Trained averaging cerebellar model controller attains very good tracking results for wide range of unlearned slower and faster trajectories, with additional improvements by relearning at faster trajectories. Inclusion of new dynamical effects to the controller results with linear growth in complexity for inputs targeting lower dendrite tree of Golgi cell, important for control applications in robotics, but not only.

show abstract

Section: Cmacgbs With Two-phase Learning As Robot Controller and Genementioning

confidence: 99%