Driven by sustaining demands from industrial automation, space applications and the lack of labor forces, robotics has received increasing attention from researchers in the field of automation and control. Optimizing control schemes is critical to fully exploit the potential of industrial and daily-use robots. Usually, accuracy and repeatability are measured to evaluate the performance of a robot, and deviation of the two parameters from normal status would inevitably leads to positional error and creates a problem for the process. Moreover, the repeatability of a robot is different in various parts of the working envelope, fluctuating with speed and payload. Due to the inherent complexity, an advanced learning methodology is crucial to the self-learning and fast adaptation to disturbances.
Intelligent control is an active field of research that brings artificial intelligence and automatic control together to solve complex control problems, such as that in robotics. This family of control techniques and algorithms spanning from traditional ones of fuzzy logic, neurofuzzy to more recent developments in brain-inspired algorithms such as neural network control, evolutionary computation etc. With recent advances in artificial intelligence, the incorporation of machine learning, self-learning and soft computing has brought new insights into this field, especially for systems without available priori mathematical model.
This Research Topic intends to bring in the latest developments in various intelligent control theory and its application to robotics. Topics of interests include but not limited to:
• Brain-inspired algorithms and application in robotic control
• Deep learning, reinforcement learning, and meta learning of autonomous systems;
• Evolved neural networks, Evolutionary fuzzy systems, and Evolved neuro-fuzzy systems;
• Neural network and fuzzy control of autonomous systems;
• Evolutionary control of autonomous systems;
• Intelligent multi-agent control systems in robotics;
• Stability and robustness analysis of intelligent control systems;
• Fuzzy inference systems, artificial neural networks, and genetic algorithms for autonomous systems.
Driven by sustaining demands from industrial automation, space applications and the lack of labor forces, robotics has received increasing attention from researchers in the field of automation and control. Optimizing control schemes is critical to fully exploit the potential of industrial and daily-use robots. Usually, accuracy and repeatability are measured to evaluate the performance of a robot, and deviation of the two parameters from normal status would inevitably leads to positional error and creates a problem for the process. Moreover, the repeatability of a robot is different in various parts of the working envelope, fluctuating with speed and payload. Due to the inherent complexity, an advanced learning methodology is crucial to the self-learning and fast adaptation to disturbances.
Intelligent control is an active field of research that brings artificial intelligence and automatic control together to solve complex control problems, such as that in robotics. This family of control techniques and algorithms spanning from traditional ones of fuzzy logic, neurofuzzy to more recent developments in brain-inspired algorithms such as neural network control, evolutionary computation etc. With recent advances in artificial intelligence, the incorporation of machine learning, self-learning and soft computing has brought new insights into this field, especially for systems without available priori mathematical model.
This Research Topic intends to bring in the latest developments in various intelligent control theory and its application to robotics. Topics of interests include but not limited to:
• Brain-inspired algorithms and application in robotic control
• Deep learning, reinforcement learning, and meta learning of autonomous systems;
• Evolved neural networks, Evolutionary fuzzy systems, and Evolved neuro-fuzzy systems;
• Neural network and fuzzy control of autonomous systems;
• Evolutionary control of autonomous systems;
• Intelligent multi-agent control systems in robotics;
• Stability and robustness analysis of intelligent control systems;
• Fuzzy inference systems, artificial neural networks, and genetic algorithms for autonomous systems.