Autonomous finding of landmarks for guiding long distance navigation by a mobile is explored. In a trial navigation, the robot continuously views and memorizes scenes along the route. When the same route is subsequently pursued again, The robot locates and orients itself based on the memorized scene. Since the stream of images is highly redundant, it is transformed into an intermediate 2(1/2)D representation, called Panoramic Representation, with much less amount of data. Although the Panoramic Representation can be used for guidance of the autonomous navigation, it still contains a huge amount of data for a very long route. A human memorizes only very impressive objects along the route such as an old church or a very high tower and uses th,em as landmarks. Our robot also finds distinctive objects along the route and memorizes their features as well as spatial relationships f o r navigation guidance. 3 0 objects along the route are segmented in the Panoramic Representation by fusing range estimates and color attributes, and th,en a structure m a p representing their arrangement in space is yielded. I n order to find distinctive objects used for the landmarks, the spatial relationsh.ips, shapes and color attributes of the objects are examined.
Most active systems use a camera mounted on a manipulator, because the control of the camera motion is easy and accurate. A limited range of the camera motion by the fixed manipulator, however, often prevents the method from real applications. This paper explores a more general method that a camera on a mobile robot freely moves in the environment and acquires the spatial information based on the active vision paradigm. The camera motion is controlled so as to fix its gaze upon a feature point and to keep the distance to the fixation point constant by visual feedback. The camera motion is determined by its rotation estimated from motions of vanishing points of horizontal lines in the environment. Non-horizontal lines are detected by their motion parallax caused by the linear motion. Experimental results show this feedback can control the camera motion within small deviations from the planned path. The deviations measured in the image are used to compensate for the errors in the 3-D position and the camera motion.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.