Mobile robot localization using a Kalman filter and relative bearing measurements to known landmarks

This paper discusses mobile robot localization using a single, fixed camera that is capable of detecting predefined landmarks in the environment. For each visible landmark, the camera provides a relative bearing but not a relative range. This research represents work toward an inexpensive sensor that could be added to a mobile robot in order to provide more accurate estimates of the robot\u27s location. It uses the Kalman filter as a framework, which is a proven method for incorporating sensor data into navigation problems. In the simulations presented later, it is assumed that the filter can perform accurate feature recognition. In the experimental setup, however, a webcam and an open source library are used to recognize and track bearing to a set of unique markers. Although this research requires that the landmark locations be known, in contrast to research in simultaneous localization and mapping, the results are still useful in an industrial setting where placing known landmarks would be acceptable