Robots have come out of industries and spread across many areas, such as agriculture, environmental protection, and services. These systems are especially useful in scenarios where humans cannot work due to their remote or dangerous nature. However, robots still have to overcome challenges related to autonomy to perform in these scenarios, as well as to reduce the workload of operators.
The rise of machine learning in recent years promises to address these issues in robotics. Deep learning techniques can be thoroughly applied to robot missions. Convolutional neural networks are providing robots with improved perception skills, whereas reinforcement learning is leading to promising results in guidance, navigation, and control. Researchers are applying other techniques to create robots with decision-making capabilities and enhance human–robot interactions.
This special session aims at collecting high-quality works that apply machine learning techniques to different types of robots (ground, aerial, marine, and submarine robots) and fleets (multi-robot systems and robot swarms). We are looking for manuscripts with state-of-the-art reviews, original research, and real-world applications.
The authors of the best articles in this special session will be offered to extend them in the special issue on Intelligent Robotics of the journal Applied Sciences.
We can offer the authors of selected papers to extend them in the special issue on Intelligent Robotics of the journal Applied Sciences.
Guidance,navigation and control
Manipulation and grasping
Ground, aerial and marine robots
Juan Jesús Roldán Gómez, Universidad Autónoma de Madrid, Spain
Mario Andrei Garzón Oviedo, Delft University of Technology, The Netherland