2025 International Conference on Advanced Robotics, Control, and Artificial Intelligence
November 24-27, 2025, Denarau​, Nadi, Fiji
Keynote Speeches
Talk: Nonlinear Modelling & Control of Micro Hands Using Learning and Operator Theory
Professor Mingcong Deng, Tokyo University of Agriculture and Technology, JAPAN
Abstract:
Learning & operator theory based robust nonlinear modelling and control design for nonlinear systems with uncertainties is shown. The relationship between operator theory and passivity for adaptive control is discussed. Meanwhile, I will introduce support vector regression (SVR) utilized for regression analysis, where the design parameters of the SVR are selected by using particle swarm optimization (PSO). In order to realize sensorless control, PSO-SVR-based moving estimation with generalized Gaussian distribution (GGD) kernel is employed. That is, learning & operator based sensorless robust adaptive nonlinear control system can be obtained. Further, current results on modeling by ant colony optimization (ACO)-MSVR for 3D actuator are shown. Finally, some current results on actuator position control for 2D/3D micro hands are introduced.
​
Bio:
Prof. Mingcong Deng (IEEE Fellow) received his PhD in Systems Science from Kumamoto University, Japan, in 1997. From 1997.04 to 2010.09, he was with Kumamoto University; University of Exeter, UK; NTT Communication Science Laboratories; Okayama University. From 2010.10, he has been with Tokyo University of Agriculture and Technology, Japan, as a professor. Now he is the Chair of Department of Electrical and Electronic Engineering. Prof. Deng specializes in three complementary areas: Operator based nonlinear fault detection and fault tolerant control design; System design on human factor based robot control; Learning based nonlinear control. Prof. Deng has over 650 publications including 220 journal papers in peer reviewed journals including IEEE Press and other top tier outlets. He serves as a chief editor for 2 international journals, and associate editors of 6 international journals. Prof. Deng is a co-chair of agricultural robotics and automation technical committee, IEEE Robotics and Automation Society; Also a chair of the environmental sensing, networking, and decision making technical committee, IEEE SMC Society. He was the recipient of 2014 & 2019 Meritorious Services Award of IEEE SMC Society, 2020 IEEE RAS Most Active Technical Committee Award (IEEE RAS Society) and 2024 IEEE Most Active SMC Technical Committee Award (IEEE SMC Society). He is a fellow of The Engineering Academy of Japan.
Talk: A New Fourier Series-based Machine Learning Framework
Professor Zhihong Man, Swinburne University of Technology, Australia
Abstract:
In this talk, a new Fourier series-based machine learning (FSML) framework is presented for the modelling of nonlinear and aperiodic input-and-output datasets. It is seen that both input and output data of a dataset are assumed to be the functional data, uniformly sampled in a fundamental period, from two continuous functions, respectively, that are the linear combination of a finite number of orthogonal trigonometric base functions. The nonlinear relationship between input and output data of the dataset can then be optimally approximated in a fundamental period. The remarkable characteristics of this research are threefold: i) Any nonlinear and aperiodic input-and-output datasets can be optimally modelled in a fundamental period with a finite number of trigonometric base functions; ii) A new data-driven based Fourier auto-encoder is developed to perform both information compression and data reconstruction; iii) From the viewpoint of frequency component reduction, a second Fourier auto-encoder is proposed to perform both information compression and feature extraction with low frequency components. A few simulation examples are presented to show the excellent learning performances of the new FSML as well as Fourier auto-encoders.
​
Bio:
Zhihong received his B.E. degree from Shanghai Jiaotong University, China, in 1982, M.Sc degree from Chinese Academy of Sciences in 1987, and PhD degree from the University of Melbourne, Australia, in 1994. From 2002 to 2007, he was the Associate Professor of Computer Engineering at Nanyang Technological University, Singapore. From 2007 to 2008, he was with Monash University Sunway Campus, served as the Professor and Head of Electrical and Computer Systems Engineering as well as the Chair of the Monash Sunway Campus Research Committee. Zhihong is currently the Professor of Robotics and Mechatronics in the School of Engineering at Swinburne University of Technology, Melbourne, Australia.
Zhihong’s research interests are in sliding mode control, robotics, neural networks-based pattern classification, vehicle dynamics & control and diagnosis of aircraft engines. He has published more than 300 research papers in refereed international journals and refereed international conferences proceedings, and his research results have widely cited more than 20000 times by the researchers from more than 30 different countries. Since 1994, Zhihong has been actively serving engineering societies as the General Chair, Program Chair, Track Chair, Session Chair, the International Advisory Committee and Technical Committees of many international conferences in control, robotics, signal processing, neural networks and industrial electronics.
In addition, Zhihong received the Nanyang Technological University Best Teacher Award in 2004 and the Most Popular Lecturer in the School of Computer Engineering at Nanyang Technological University Singapore from 2002 to 2007, respectively.
Talk: Leveraging Digital Transformation and AI for Next-Generation Aviation Training in the South Pacific
Abstract:
This keynote address details the Fiji Airways Aviation Academy's (FJAA) strategic use of Industry 4.0 principles to sustain and optimize a world-class four-fleet of CAE 7000XR Level-D simulators. We examine the current state of Digital Operational Excellence at the Nadi facility, highlighting the Simorg management platform's critical role as a real-time control system for asset utilization, crew scheduling, and stringent regulatory compliance.
The core focus is on the future strategic planning around AI and data analytics. We discuss how FJAA is refining its data pipelines to align with the global shift towards Objective Performance-Based Training (OPBT), exemplified by systems like CAE Rise. Furthermore, we outline the groundwork being laid for Predictive Maintenance, actively exploring how foundational sensor data and Machine Learning could maximize critical asset uptime and guarantee regional training resilience. This provides a crucial industry perspective on building a robust, technology-aligned future for Pacific aviation.
​
Bio:
Shivneel Prasad is Lead Simulator Engineer at the Fiji Airways Aviation Academy, overseeing four CAE 7000XR Level-D full-flight simulators for B737 MAX, A330, A350, and ATR72-600 aircraft. A University of the South Pacific alumnus, he specializes in advanced control systems, real-time data analytics, and AI integration.
Shivneel drives FJAA’s digital initiatives, enhancing simulator reliability through predictive maintenance and preparing infrastructure for Objective Performance-Based Training (OPBT) with high-fidelity flight data. His efforts ensure EASA/CAAF compliance and operational resilience in the Pacific’s unique environment.
At ARCAI 2025, he presents FJAA’s leadership in applying AI and Industry 4.0 to deliver adaptive, data-driven pilot training—establishing the region as a hub for next-generation aviation excellence.