EVIDENCE ACCUMULATION USING BINARY FRAMES OF DISCERNMENT FOR VERIFICATION VISION

An important aspect of sensor-based robotics is task verification, where a simple example is the verification of object placement using vision sensors. Vision sensor output can be processed to yield a multitude of low-level measurements, where each is inherently uncertain, which must somehow be combined to verify the location of an object. In this paper, we have shown that this combination can be accomplished via Dempster-Shafer theory using binary frames of discernment (BFOD). A special advantage of BFOD is the computational ease with which they allow information from disparate sources to be combined—which is particularly significant in light of recent concerns about the exponential complexity of a brute-force implementation of this theory. © 1990 IEEE