Service and collaborative robots are becoming more common in dynamic human inhabited environments. Robots have potentially a wide range of capabilities, making them the perfect candidates for the role of general assistive devices. To be fully effective, robots must adapt to their end users’ needs. Users, however, may lack the technical skills to properly instruct robots to their needs. For this reason, robots should learn from people in a natural yet effective way.
What we do
- Analyse robot learning paradigm like Learning from Demonstration (LfD) and Active Learning (AL) from the Human-Robot Interaction
- Integrate learning techniques into End-User Programming frameworks
Service robots will be deployed in the future as general assistive devices in dynamic human environments like households, schools and hospitals. In order to be valuable and cost-effective assistants, robots must allow a wide range of customization, especially regarding their skills. As pre-programming robots for every situation is impossible, robots need to gain new skills […]