Although mechanization has lowered management costs and precision viticulture is shyly bursting, selective practices still require time-consuming manual operations. This project tackles the emerging challenge of the dramatic shortage in skilled labor and lower grape price using robotic solutions. Robots are a revolutionary upscaling in the Agri- Food sector for their precision and efficiency. The main goal of this project is to develop and test innovative robotic mobile manipulation technologies for grapevine winter pruning automation. Deep learning processes and pruning skills will be merged into a robot with advanced control capabilities. Multi-modal sensing system, in particular stereo vision, will be developed and integrated to a full torque sensing robotic manipulator for grapevine recognition, manipulation, and pruning. This robotic arm will be mounted on a legged locomotion platform forming a mobile manipulator prototype that will be demonstrated in comparison with hand pruning in vineyard. Robot manipulation performance as pruning efficiency, locomotion as related to different terrain as well as vine growth features the following season will be assessed. Impacts of the project embrace the still unreached goal of selective and fully automation of winter pruning.

For more information, please contact the responsible of the UNINA research unit [fabio (dot) ruggiero (at) unina (dot) it].

WELDON is aimed at enhancing the autonomy of bipedal robots, such as humanoids, for future application to manufacturing, service robotics, and healthcare domain. Recent robotic challenges have shown that humanoids exhibit serious robustness problems within unstructured scenarios. On the other hand, robot manipulation capabilities are daily increasing, filling the actual gap between human and robotic skills. Latest funded projects in robotics have demonstrated that robots can perform complex manipulation tasks like the nonprehensile ones, where the object is manipulated without being caged within the hand’s fingertips or the palm. A new trend in robotics is to find out possible connections between different research fields. By using existing techniques in a specific robotic sector, it is then possible to export the discovered tools into the connected scenario to solve some issues. To this purpose, literature has already highlighted that balancing, slow walking gaits, and grasping tasks share several similarities. For instance, two slow walking legs can be seen as two fingers grasping a much larger object, i.e., the earth. However, walking shares also some hybrid contact/non-contact conditions with a multi-fingered hand juggling some objects on it. Since the robotic manipulation theory is indeed advanced during the last decades, the fundamental idea behind WELDON is to establish a connection between multi-contact dynamic, energy efficient walking and nonprehensile manipulation. Find out such a connection will allow to WELDON to go beyond the current scientific state of the art in legged robotics, providing both theoretical and technological solutions where cutting-edge knowledge and innovation can merge in creating e versatile framework for walking tasks.

For more information, please visit the project website, or contact the principal investigator [fabio (dot) ruggiero (at) unina (dot) it].

During the Maker Faire Rome 2017, European Edition, the RoDyMan stand has been awarded Maker of Merit for its originality and potential, a certificate issued by the organizers and the American mother company. Fabio Ruggiero was responsible for the RoDyMan stand during the three days, from December 1 to December 3, 2017. See the related press coverage on the PRISMA Lab website.