Three-dimensional ultrasonic vision for robotic applications

Considers a vision system that uses the echo of a transmitted ultrasonic pulse as the basis for identifying objects. The return of a single pulse from an object generates a three-dimensional acoustical characteristic signature across the aperture of a receiving antenna which can be directly used for object identification. Thus, there is no need to reproduce an accurate visual representation to recognize which of a class of objects is present. Since the signal bandwidth is narrow relative to that of an optical imaging system, faster execution should be possible. The need to remove clutter which can arise in a conventional imaging system, caused by the compression of three dimensions into two, is totally avoided. The authors calculate a fundamental limit (in the Shannon sense) on the number of objects that can be distinguished by an ultrasonic system and show that, for modest signal-to-noise ratios and an object space comparable to the beamwidth, an enormous number of different objects can still, in principle, be resolved