Interaction with Robot Assistants: Commanding ALBERT

Giving advice to a mobile robot assistant still requires classical user interfaces. A more intuitive way of commanding is achieved by verbal or gesture commands. In this article, we present new approaches and enhancements for established methods that are in use in our laboratory. Our aim is to interact with a robot using natural and direct communication techniques, and through this means coping with complex robot programs. Using skin color segmentation algorithms for tracking a user’s hand, Fourier Descriptors of it’s outline are computed in order to map hand shapes to gesture classes. Recognized gesture types and manipulable objects as well as verbal commands are fed into an event manager that selects and starts an appropriate reaction. This architecture has proven it’s applicability to human-machine interaction in first experiments and will be expanded in the near future.