Guest Editor(s)
Prof. Dr. Abdul Rehman
Email: a.rehman.jj@jj.ac.kr
Affiliation: Research Institute of Engineering & Technology, Jeonju University, Jeonju, South Korea
Homepage:
Research Interests: artificial intelligence, machine learning, deep learning, data science, soft computing, signal processing, computer vision, IoT and industrial IoT, cyber-physical systems, intelligent automation, autonomous systems, AI-driven adaptive and learning-based control
Dr. Faisal Saeed
Email: bscsfaisal821@gmail.com
Affiliation: Department of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China
Homepage:
Research Interests: artificial intelligence in healthcare; explainable AI; trustworthy AI; explainable large language models
Dr. Muhammad Diyan
Email: m.diyan@tees.ac.uk
Affiliation: Department of Computing & Games, Teesside university, Middlesbrough, U.K.
Homepage:
Research Interests: internet of things; smart homes; web of things; big data analytics; vehicular ad hoc networks; intelligent systems
Summary
Intelligent autonomous systems are increasingly expected to operate in uncertain, dynamic, data-rich, and safety-critical environments, including autonomous vehicles, UAVs, robotics, smart manufacturing, smart grids, IoT/IIoT platforms, and cyber-physical systems. Classical adaptive control provides strong foundations for handling nonlinear dynamics, disturbances, and parameter variations; however, modern autonomous systems also face incomplete models, noisy sensing, actuator constraints, communication delays, cyber-physical threats, multi-agent interactions, and real-time decision-making requirements.
This Special Issue aims to provide a timely forum for high-quality research on AI-driven adaptive and safe learning control for intelligent autonomous systems under uncertainty. It seeks to bridge adaptive control theory, artificial intelligence, soft computing, reinforcement learning, data-driven optimization, digital twins, edge intelligence, and trustworthy autonomous decision-making. Contributions are expected to advance control solutions that are not only accurate and adaptive, but also stable, robust, explainable, safe, computationally efficient, and deployable in realistic engineering environments.
Suggested themes include, but are not limited to:
• AI-driven adaptive control for nonlinear and uncertain autonomous systems
• Safe learning-based control with stability, robustness, and safety guarantees
• Reinforcement learning and deep reinforcement learning for real-time autonomous control
• Neural, fuzzy, neuro-fuzzy, and soft-computing-based adaptive control methods
• Data-driven, model-free, and hybrid model-learning control strategies
• AI-assisted model predictive control and adaptive dynamic programming
• Robust, resilient, and fault-tolerant control under disturbances, delays, faults, and cyber-physical threats
• Digital twin-enabled adaptive control, simulation-to-real learning, and intelligent monitoring
• Explainable, trustworthy, and human-in-the-loop AI for control and automation
• Edge intelligence and real-time learning control for resource-constrained autonomous platforms
• Multi-agent, distributed, and cooperative adaptive control systems
• Applications in robotics, UAVs, autonomous vehicles, smart manufacturing, smart grids, IoT/IIoT, and cyber-physical systems
The Special Issue especially welcomes theoretical, methodological, experimental, and application-oriented studies with clear novelty, rigorous validation, reproducible evaluation, and practical relevance to intelligent automation and soft computing.
Keywords
AI-driven adaptive control, safe learning control, reinforcement learning, neural and fuzzy adaptive control, data-driven control, autonomous robotic systems, industrial cyber-physical systems, intelligent automation, digital twins, soft computing
Login
Register
Submit a Paper
Propose a Special lssue