Cognitive instruction interface for mobile robot navigation

Abstract

An essential aspect distinguishing robotics from other areas of artificial intelligent is their interaction with humans and their surrounding environments. Spatial knowledge can be represented in various ways to increase the interaction between human users and mobile robots. One effective way is to describe the route verbally to the robot. This method can permit inexpert users to instruct their mobile robots, which understand spatial descriptions, to naturally perform complex tasks using succinct commands. We present a spatial language to describe route-based navigation tasks for a mobile robot. The instructions of this spatial language are implemented to provide an intuitive interface with which computer language nai¿ve user can easily and naturally describe a navigation task to a mobile robot in any indoor environment. In our system, the instructions of the processed route are analyzed to generate a symbolic representation of the navigation task via the instruction interpreter. The resulting symbolic representation is used to generate a graphical representation of the route to supply the robot with the information about the route's environment and the relationships between the landmarks. It is also supplied to the robot motion planning stage as initial path estimation of route description and to ground the landmark symbols with their equivalent physical objects by using perceptual anchoring.