Sensory Channel Group and Structure from Uninterpreted Sensor Data

In this paper we focus on the problem of making a model
of the sensory apparatus from raw uninterpreted sensory
data as defined by Pierce and Kuipers (Artificial Intelligence
92:169-227, 1997). The method relies on generic
properties of the agent’s world such as piecewise smooth
effects of movement on sensory features. We extend a previously
described algorithm with an information-theoretic
distance metric that can find informational structure not
found by the original algorithm. We also use the method
to create metric projections of the sensory and motor systems
of a robot. Data from a real robot show that the metric
projections for example can be used to distinguish the vision
sensors from all other sensors and also to find their
functional layout. Finally we present an application of the
method where the real layout of the vision sensors is found
from scrambled vision data.