Ontologies and Conceptual Metaphor in Autonomous Robotics

mobile robots can make use of fuzzy processing and computing with words in order to extend their capabilities by allowing them to be less literal and exact match oriented. Both sensor data interpretation and planned activities subtleties benefit from fuzzy inexact processing.[1] The sciences of astronomy and physics have long used conceptual metaphor productively, in such terms as " event horizon " , " gravity well " , " curved space " , " time dilation ". The same technologies which provides the mechanisms for such term usage are available to robotic and geo-spatial processing.[2] Productive conceptual metaphors can be used functionally on computers. I.INTRODUCTION obile robots operating outside the closed world of the factory face a much more complex working environment. Not only is there the open-world "other agents" problem to deal with but the objects and situations are more diverse and complex. Whereas precision and exactitude is desired in bridge building often it is not attainable in the unstructured natural environment. Being able to handle imperfect sensor data provides a mobile robot with an extra measure of coping. Having programming which governs the robot which does not use or require high-precision is also useful in adequately dealing with the unstructured natural environment. In the case of the DARPA Grand Challenge the programmers of the participating vehicles had some idea of the kinds of things they would need sense and deal with, objects, paths and depressions, for example. A robot system such as OPRS permits one to set up pre-programmed "notions" (representations in memory) for paths, way points, obstacles, for example and derive the presence of these by examining sensor data. Typically, the way points and obstacles may be treated as fixed things at a given location, which is not time varying. These constructs may be handled succinctly by means of relatively simple scalar representations of location, size and so on. Planning the path of travel, a typical job of on board computing systems in an autonomous mobile robot, might be performed using the A* approach [3] [4] [5] [6]. The robot drive system itself requires specific instructions to operate with it cannot use inexact, waffle values. Approaches such as A* provide the system with point locations (exactitude) with which to operate. We see in this paper means of effectively fuzzifying approaches such as A*. II.SITUATED Deciding what to do and planning benefit from a tolerance of inexact reasoning …