Symmetry as a basis for perceptual fusion

Robot Cognition using Bayesian Symmetry Networks

“…Suppose that data from a single object (a square) is to be analyzed. Figure 6 shows a number of group elements that can be discovered by symmetry detectors applied to image data of a square; this includes translation, reflection and rotation symmetries; we have described symmetry detectors for 1D, 2D and 3D data elsewhere [8,7,9]. The symmetry groups would allow the synthesis of ℜ ≀ D 4 (this is the same as ℜ × ℜ × ℜ × ℜ ⋊ D 4 ) as a representation of the data.…”

“…), although some aspects of the robot's knowledge may be learned from experience. This approach to establishing robot cognitive faculties does not scale well, and as a more effective and efficient paradigm, we have proposed that a collection of symmetry theories form the basic innate knowledge of an autonomous agent [5,8,7,9]. These are defined as formal, logic-based systems, and then the robot proceeds to use this knowledge by analyzing sensorimotor data to discover models for the theories.…”