About this Research Topic
Multi-robot systems, including autonomous vehicles, unmanned ships, and manipulators, have become an essential part of modern industry since they can execute time-sensitive, complex, and large-scale problems that are intractable for single robots. The development of artificial intelligence has brought about significant further advancements in multi-robot systems. One of the most promising areas is learning and control, which aims to create smarter robots that can adapt to new situations quickly. Neural networks are capable of processing vast amounts of data and recognizing patterns that would be difficult or impossible for humans to detect. As a result, they could be used to improve the capability of multi-robot systems to a significant degree.
The primary goal of this Research Topic is to provide a platform for researchers from academia to share their latest findings on the topic of learning-based coordinated control for multi-robot systems. We aim to promote discussion around cutting-edge research methods, algorithms, theories, and emerging challenges in this area. Specifically, we seek contributions addressing topics such as dynamic learning-based control for robotic systems, cooperative reinforcement learning-based control for multi-robot systems, and machine learning in multi-robot control systems. We encourage submissions that report novel results demonstrated through experiments either with real-world robots or simulations thereof.
We invite original research articles that report new advances or significant results related to neural learning-based control techniques in multi-robot systems, such as autonomous vehicles, unmanned ships, manipulators, and multi-robotics. Topics include but are not limited to:
• Dynamic learning from neural control for uncertain multi-robot systems
• Cooperative (deep) reinforcement learning-based control for collaborative robot systems
• Neural-network-based iterative learning control for multi-robot systems
• Machine learning in multi-robot coordination control systems
• The robustness and convergence analysis of the dynamic learning/reinforcement learning/iterative learning/machine learning algorithms
The primary goal of this Research Topic is to provide a platform for researchers from academia to share their latest findings on the topic of learning-based coordinated control for multi-robot systems. We aim to promote discussion around cutting-edge research methods, algorithms, theories, and emerging challenges in this area. Specifically, we seek contributions addressing topics such as dynamic learning-based control for robotic systems, cooperative reinforcement learning-based control for multi-robot systems, and machine learning in multi-robot control systems. We encourage submissions that report novel results demonstrated through experiments either with real-world robots or simulations thereof.
We invite original research articles that report new advances or significant results related to neural learning-based control techniques in multi-robot systems, such as autonomous vehicles, unmanned ships, manipulators, and multi-robotics. Topics include but are not limited to:
• Dynamic learning from neural control for uncertain multi-robot systems
• Cooperative (deep) reinforcement learning-based control for collaborative robot systems
• Neural-network-based iterative learning control for multi-robot systems
• Machine learning in multi-robot coordination control systems
• The robustness and convergence analysis of the dynamic learning/reinforcement learning/iterative learning/machine learning algorithms
Keywords: Neural network control, Learning control, Dynamic learning, Reinforcement learning, Machine learning, Adaptive control, Robotics, Autonomous Vehicles, Unmanned ship, Unmanned aerial vehiclem Manipulators, Multi robotics
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
