Research Area:  Metaheuristic Computing
This paper presents a hybrid metaheuristic embedded system for intelligent vehicles using hypermutated firefly algorithm (FA)-optimized radial basis function neural network (RBFNN), called FA-RBFNN. With the Mecanum vehicle-s dynamic model, the FA with hypermutation is fused with RBFNN to develop a real-time optimal controller of the four-wheeled Mecanum vehicles in a field-programmable gate array (FPGA) chip. This hybrid metaheuristics takes the benefits of neural network, FA, real-time control, and FPGA realization. All the FA-RBFNN, dynamic controller, and hardware circuits are implemented in one FPGA chip using System-on-a-Programmable Chip methodology. Comparative works and experimental results clearly illustrate that the proposed FPGA-based FA-RBFNN optimal controller outperforms the conventional control methods.
Keywords:  
Metaheuristic
neural network
optimization
redundant control
Author(s) Name:  Hsu-Chih Huang; Shao-Kang Lin
Journal name:  IEEE Transactions on Industrial Informatics
Conferrence name:  
Publisher name:  IEEE
DOI:  10.1109/TII.2018.2796556
Volume Information:  Volume: 15, Issue: 2, February 2019,Page(s): 1062 - 1069
Paper Link:   https://ieeexplore.ieee.org/abstract/document/8267134