The DoD needs cognitive psychologists!

SBIR call for “A psychologically inspired object recognition system”

The DoD has put out a call for proposals for the development of an object recognition system for computers that obeys psychological principles. Object recognition is obviously important for humans, and as more robots are being used in place of humans, they should also be able to identify objects to aid in mission success. The project description sounds like a short review of the object recognition literature, in fact (emphasis added by me):

Recognizing and identifying an object from a video input turns out to be a very difficult problem. The problem stems from the fact that a single object can be viewed from an infinite number of ways. By rotating, obscuring, or scaling a single object, one can create multiple representations of an object - which makes the problem of matching the object to a database of objects very difficult. The problem expands exponentially when objects that need to be identified have never been viewed before. Combine these limitations with the wide variety of objects which might be identified, and the problem becomes intractable. One solution is to study and understand how human beings recognize objects in the real world and duplicate that functionality in a series of algorithms. Recent research (Tarr and Bulthoff, 1995) has indicated that humans use not one algorithm, but multiple algorithms for the task of object recognition - depending on the object being recognized and the situation at hand. Specifically, research has shown that people use template based algorithms (i.e. similar to the database matching algorithms described earlier) in addition to Geon based (Beiderman, 1995) algorithms and feature based algorithms.

First of all, 1995 counts as recent research? Sounds like some DoD scientists need to attend the Vision Sciences conference. Secondly, it is satisfying to see that the DoD believes that understanding how the human mind works is a big step in implementing human-like cognition in artificial systems.

This is similar to the field of biorobotics, where the understanding of how natural organisms work (say, a dolphin) can be applied to machines (say, a submarine). This makes a lot of sense, actually. Biological organisms are highly evolved - nature has done the work of choosing what works best. By studying what works best, we can use those principles in designing our own machines. It seems like a new principle in engineering, but it makes a lot of sense.