ECAI 2004 Conference Paper

Interactive Task Planning through Multiple Abstraction: Application to Assistant Robotics

Cipriano Galindo, Juan-Antonio Fernandez-Madrigal, Javier Gonzalez

Humans, in particular non-expert people, are the most important element within the environment of assistant robots. In this kind of applications, robots must possess a symbolic world model in order to plan efficiently the tasks requested by users, which should be specified and supervised in a human-like manner. Therefore, the internal world model of the robot must be suitable for human interaction with the task planning process. If a single model is used both for task planning and for human-robot communication, it may be non optimal with respect to both operations. In this paper, a task planning scheme is proposed to face efficiently both problems in assistant robot applications through a multihierarchical world model.

Keywords: Robotics, Task planning, World model, Human-robot interaction

Citation: Cipriano Galindo, Juan-Antonio Fernandez-Madrigal, Javier Gonzalez: Interactive Task Planning through Multiple Abstraction: Application to Assistant Robotics. In R.López de Mántaras and L.Saitta (eds.): ECAI2004, Proceedings of the 16th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2004, pp.1015-1016.

ECAI-2004 is organised by the European Coordinating Committee for Artificial Intelligence (ECCAI) and hosted by the Universitat Politècnica de València on behalf of Asociación Española de Inteligencia Artificial (AEPIA) and Associació Catalana d'Intel-ligència Artificial (ACIA).