# YoubotResearch

The KUKA Youbot is a mobile manipulator primarily developed for education and research, launched in Sept 2010. We started developing applications when it was not yet in production thanks to an early prototype. We hope that it will become a standard platform for the community that is interested in education and research in mobile manipulation.

Several projects have been developed with the KUKA Youbot platform and others are in going.

### Programming by Demonstration of Everyday Tasks

L. Peppoloni, A. Di Fava, E. Ruffaldi, C. Avizzano, "A ROS-integrated architecture to learn manipulation tasks from a single demonstration", IEEE RO-MAN, 2014

;

 This project presents an integrated robotic system capable of learning and executing manipulation tasks from a single human user’s demonstration. The system capabilities are threefold. The system learns tasks from perceptual stimuli, models and stores the information in the form of semantic knowledge. The system may employ the model achieved to execute task in an way similar to the example shown and adapt the motion to robot own constraints in terms of physical limits and interferences. The system integrates perception and action algorithms in order to autonomously extrapolate the context in which to operate. It robustly changes its behavior according to the environment evolution. The system run on the Kuka Youbot platform and all the tools and algorithms are integrated into Willow Garage ”Robotic Operating System” (ROS).

### Youbot and BCI integration

 The integration of robotic manipulator with Brain-Computer-Interface have been recently explored. The aim is to provide robotic assistance to severely impaired and locked-in subjects, who have lost almost or all the motor control of the body. BCI systems can retrieve communication functionalities from the brain signals, thus allowing the patient to control assistive robotic devices directly by his mental activity. In particular, not-invasive BCIs based on EEG signals have been implemented for the remote control of a mobile robot capable of reaching and grasping tasks of generic objects. The BCI processing algorithm was based on motor imagery, a method that detects features of the brain waves related to the imagination of motor tasks, resulting into a highly intuitive and natural interface for the patient. The main drawbacks of the Motor Imagery method, the lack of d.o.f of the identified imaginary movement, was compensated through the artificial intelligence of the robot: environment mapping, obstacle avoidance, object and proper task reckognition were all features autonomously processed by the robot.
The Team working on the YouBot is composed of: Alessandro Di Fava and Lorenzo Peppoloni.
Project Leaders: Emanuele Ruffaldi and Carlo Alberto Avizzano