Natural Language Access to Intelligent Robots: Explaining Automatic Error Recovery

The increasing intelligence and autonomy of modern robot systems requires new and powerful man-machine-interfaces. For example, a robot' s capability to autonomously recover from error situations corresponds with dynamic adjustments of robot plans during execution. This makes it difficult for an operator to predict and understand the behaviour of the machine. Explanations and descriptions of why and how a certain plan has been changed would impose the acceptance of robots. Descriptions are even more important in error situations which can not be handled autonomously. In this context, natural language is an effective tool of using robots in a more flexible manner. In this article, the joint efforts of the University of Karlsruhe and the University of Saarland to provide a natural language explanation for the error recovery of the autonomous, mobile, two-arm robot, KAMRO are reported. In: A.M. Ramsay (ed.): Artificial Intelligence: Methodology, Systems, Applications, Proc. of AIMSA'96, Sozopol, Bulgaria, September 1996, Amsterdam: IOS Press, 259–267.