Project Description: Data-driven modeling is a technique, where the parameters and components of a model are determined based on the characteristics of some set of observations of an unknown system, such that the model best describes the observations. The major drawback in these methods frequently manifests as unpredictable outcomes and the absence of guarantees about the stability of the control loop and performance limitations, which is translated as compromised safety in control systems. Therefore, the current application of data-driven approaches in control is often limited to non-critical and/or low-performance systems.  As the number of robots increases, current control algorithms mainly based on centralized approaches and/or parametric models bottleneck in the real world. Therefore, there is a real technological need to construct decentralized data-driven control algorithms with safety guarantees satisfying real-world requirements.  This project aims at developing decentralized control strategies with data-driven modeling for (underactuated) multi-rotor unmanned aerial vehicles which are cooperating in a task (supervision of areas, transportation of objects,…).  The combination of theory with experimentation and the multi-disciplinary nature of the approach will result in an improvement from the conventional usage of data-driven control algorithms. In particular, for the implementation of robust control algorithms in cooperative tasks with multi-rotor unmanned aerial vehicles (drones). 

Project Description: Coordinated motions for robotic swarms are employed in a large variety of field applications such as inspecting an area for search and rescue operations, environmental monitoring or, supporting fire extinction works. Coordination is crucial when robots cooperate to conduct a task, as for instance the transportation of objects and rescue missions in disaster areas. As the number of robots in the swarm increases, current coordination algorithms mainly based on centralized approaches bottleneck in the real world. Therefore, there is a technological need to construct decentralized control algorithms satisfying real-world requirements. This project aims at developing decentralized coordinated motions (the strategies) for complex multi-robot systems (robotic swarms) which are cooperating in a task. The combination of theory with experimentation and the multi-disciplinary nature of our approach based on geometric control will result in an improvement from the conventional usage of control algorithms. In particular, for the implementation of robust control algorithms in transportation with drones and cooperative surveillance tasks with complex multi-robot systems as multiples unmanned aerial and ground vehicles.