Spatial Learning for Robot Locialization

Balakrishnan, Karthik and Honavar, Vasant (1997) Spatial Learning for Robot Locialization. Technical Report TR97-08, Department of Computer Science, Iowa State University.

Abstract

Although evolutionary algorithms have been
employed to automatically synthesize
control and behavior programs for robots
and even design the physical structures of the robots,
it is impossible for evolution to anticipate
the detailed structure of specific environments that the robot might
have to deal with. Robots must thus possess mechanisms
to learn and adapt to the environments they encounter.
One such mechanism that is of importance to {\em mobile
robots} is that of spatial learning, i.e., the ability to
learn the spatial locations of objects and places in the environment,
which would allow them to successfully explore and navigate in
a-priori unknown environments.
This paper proposes a computational model for the acquisition and use of
spatial information that is inspired by the role of the
{\em hippocampal formation} in animal spatial learning and navigation.


Subjects:
All uncategorized technical reports


ID code:
00000153
Deposited by:
Staff Account on 02 April 1997





Contact site administrator at: ssg@cs.iastate.edu