Mediating between qualitative and quantitative representations for task-orientated human-robot interaction.

摘要

In human-robot interaction (HRI) it is essential that the robot interprets and reacts to a human’s utter-ances in a manner that reflects their intended mean-ing. In this paper we present a collection of novel techniques that allow a robot to interpret and ex-ecute spoken commands describing manipulation goals involving qualitative spatial constraints (e.g. “put the red ball near the blue cube”). The result-ing implemented system integrates computer vi-sion, potential field models of spatial relationships, and action planning to mediate between the contin-uous real world, and discrete, qualitative represen-tations used for symbolic reasoning. 1