Path Based Mapping Technique for Robots
This addresses mapping uncertainty for indoor robots, though it appears incremental as it trades off efficiency for accuracy.
The paper tackles the problem of uncertainty in autonomous robot mapping by proposing a path-based approach that breaks indoor environments into reachable areas and objects with boundaries, eliminating uncertainties at the cost of temporal efficiency while using only cheap infrared sensors.
The purpose of this paper is to explore a new way of autonomous mapping. Current systems using perception techniques like LAZER or SONAR use probabilistic methods and have a drawback of allowing considerable uncertainty in the mapping process. Our approach is to break down the environment, specifically indoor, into reachable areas and objects, separated by boundaries, and identifying their shape, to render various navigable paths around them. This is a novel method to do away with uncertainties, as far as possible, at the cost of temporal efficiency. Also this system demands only minimum and cheap hardware, as it relies on only Infra-Red sensors to do the job.