Why is it so hard to talk to a machine? If only we could communicate in
a natural human language with robots, they would be so much more
useful. Having machines that can reason spatially and receive and
communicate such reasoning linguistically will extend their utility in
many more scenarios that are dangerous, tedious, unhealthy, etc. Scene
description, involving linguistic expressions of the spatial
relationships between image objects, is a major goal of high-level
computer vision. People have studied spatial relationships for several
years. In a series of papers, we have introduced the use of histograms
of forces to produce evidence for the description of relative position
of objects in a digital image. There is a parameterized family of such
histograms, for example, the histogram of constant forces (much like
the earlier histogram of angles) and the histogram of gravitational
forces that highlights areas that are close between the two objects.
Utilizing the fuzzy directional membership information extracted from
these histograms within fuzzy logic rule-based systems, we have
produced high-level linguistic descriptions of natural scenes as viewed
by an external observer. Additionally, we have begun to exploit the
theoretical properties of the histograms to match images that may be
the same scene viewed under different pose conditions. In fact, we can
even recover estimates of the pose parameters. These linguistic
descriptions have then been brought into an ego-centered viewpoint for
application to robotics. We describe three initial activities here:
production of linguistic scene description from a mobile robot
standpoint, spatial language for human/robot communication, and
understanding of a sketched route map for communicating navigation
routes to robots. These efforts just scratch the surface of the
potential applications and we end with future projections.
|