Carl, a learning robot, serving food at the AAAI reception

Abstract

The development of robots able to accept, via a friendly interface, instructions in terms of the concepts familiar to the human user remains a challenge. Designing and building such intelligent robots can be seen as the problem of integrating four main dimensions: human-robot communication, sensory motor skills and perception , decision-making capabilities and learning. Although these dimensions have been thoroughly studied in the past, their integration has seldom been attempted in a systematic way. For the common user, a sufficiently practical interface must include spoken language. These issues are being studied at our institute in the framework of the project CARL (Communication, Action, Reasoning and Learning in Robotics). The AAAI Hors d'Ouevres competition seemed to be an interesting setting for evaluating and demonstrating the project's robot, naturally called 'Carl'. This paper describes the body and soul of Carl as well as the lessons learned from the participation in the competition.