Research Topics

The execution of missions with robotic systems in the marine environment is a challenging task since it implies the control of non-linear systems in an unstructured environment where communication and localization can mainly rely on acoustic, low-frequency devices. Since more than twenty years, the research team is actively working on the development of control techniques for underwater robots, as Autonomous Underwater Vehicles (AUVs) and Remotely Operated Vehicles (ROVs) eventually equipped with manipulators, to perform autonomous missions. Large part of the activities in this field are carried out as a Unit of Interuniversity Center on Integrated Systems for Marine Environment (ISME) with witch the group has participated to a large number of national and European Research projects.

The field of cooperation and coordination of multi-robot systems has been object of considerable research efforts in the last years. The basic idea is that multi-robot systems can perform tasks more efficiently than a single robot or can accomplish tasks not executable by a single one. Moreover, multi-robot systems have advantages like increasing tolerance to possible vehicle fault, providing flexibility to the task execution or taking advantage of distributed sensing and actuation. Such systems can be used in many applications like, e.g., exploration of an unknown environment, navigation and formation control, demining, object transportation, up to playing team games (e.g., soccer). In this framework, the group has developed and tested several centralized and distributed control strategies for teams of autonomous mobile robots (i.e. mobile robots, underwater robots and surface vessels). 

People affected by severe motor impairments might find difficult or impossible to perform daily life activities, such as getting dressed or fed, and, thus, require a constant presence of caregivers for assistance. In this context, robotic systems can certainly help such people in improving their life quality by providing some sort of autonomy in executing some activities and by reducing the needs of a constant presence of a caregiver. Among the possible Human-Machine Interfaces (HMIs),  Brain Computer Interfaces (BCIs) can allow users to command robotic devices using only Electroencephalographic  (EEG) signals. In this context, we developed supervisory and shared control architectures based on Event Related Potentials (ERPs), as P300, or on motor imagery to control mobile robotics manipulators to perform assistive tasks. 

Robot manipulation in precision agriculture is revolutionizing farming by combining advanced technology with human expertise. These AI-powered robots, equipped with sensors, work alongside farmers to perform tasks like planting, pruning, and harvesting with exceptional precision. This collaboration enhances efficiency, allowing farmers to focus on strategy while robots handle repetitive or labor-intensive work. Together, they gather real-time data on soil health and crop growth, enabling smarter decisions and sustainable practices.  By minimizing waste and optimizing resources, this human-robot partnership promotes eco-friendly farming and improves crop quality.  Benefits are reduced labor costs and increased productivity, making it a valuable solution for farms of all sizes. As technology advances, robotized solutions will play a key role in sustainably feeding a growing global population.

Aerial robotics is transforming industries with drones that inspect infrastructure, monitor construction sites, and assess disaster zones quickly and safely. They deliver supplies to remote areas, track wildlife, and monitor environmental changes like deforestation and climate impacts. From logistics to conservation, drones are making tasks faster, safer, and more efficient, proving their value across countless applications. The control and integration of sensors and systems in aerial robotics is a rapidly advancing field that focuses on enabling unmanned aerial vehicles (UAVs) to operate with precision, autonomy, and intelligence. By combining advanced control algorithms with sophisticated sensor technologies, drones are capable of navigating complex environments, making real-time decisions, and performing tasks with high accuracy. This integration allows UAVs to perceive their surroundings through cameras, LiDAR, and other sensors, process the data onboard, and execute precise movements or actions.

Learning in robotic manipulation enables robots to acquire and refine skills through experience, using machine learning and AI to perform tasks like grasping, lifting, and assembling with precision. This approach allows robots to adapt to new situations, improving their efficiency and flexibility. Applications span industrial automation, healthcare, and household assistance, where robots learn to handle delicate tasks or collaborate with humans. By advancing learning-based methods, researchers are making robots more intelligent and capable, unlocking their potential to solve complex real-world challenges.

The group has a more than thirty years experience on the use of industrial and service robotic manipulators. In particular, the gorup has actively worked on aspects related to:
- Inverse kinematics algorithm for redundant manipulators;
- Identification techniques for the estimation of the robot’s dynamic parameters;
- Cooperative control of multiple manipulators.