An Automatic Generator of Presentations for Tour-Guide Robots

This paper proposes an automatic presentation generator for a robot guide. The presentations are formed by groups of paragraphs. The selection of the best paragraphs is based on a semantic understanding of the characteristics of the paragraphs, on the restrictions defined for the presentation (time, contents, cultural level, etc.) and by the quality criteria appropriate to a public presentation. This work is part of the ROBONAUTA project of the Intelligent Control Research Group at the Universidad Politecnica de Madrid (UPM) to create "awareness" in a robot guide. The software developed in the project has been verified on the tour-guide robot Urbano. The most important aspect of the proposal is that the design uses learning as the means to optimize the quality of the presentations. The means to learn new knowledge is based on access to the Internet. The means to learn about quality criteria is based on a process of tutelage. The means to learn about the quality of a given presentation is based on a feedback loop using the opinions of the public in attendance. The modeling of the index of quality of the presentation is made using fuzzy logic and represents the beliefs of the robot about what is good, bad, or indifferent about a presentation. This fuzzy system is used to select the most appropriate group of paragraphs for a presentation. The "beliefs" of the robot continue to evolve in order to coincide with the opinions of the public. It uses a genetic algorithm for the evolution of the rules.