Publikation
From Rule Extraction to Active Learning Symbol Grounding
Henrik Jacobsson; Geert-Jan Kruijff; Maria Staudte
In: Proceedings of the ICRA-07 Workshop on Concept Learning for Embodied Agents. ICRA Workshop on Concept Learning for Embodied Agents, located at ICRA 2007, Rome, Italy, IEEE, 4/2007.
Zusammenfassung
The paper focuses on a fundamental learning problem in adaptive, embodied cognitive systems: Namely, how
to learn discrete models of situated, embodied experience which
can act as a mediation between sensori-motoric experience and
high-level cognitive processes. The paper suggests to address
the problem using a combination of bottom up active learning
of embodied concepts solely on the basis of the actions and
perceptions of the robot, and top-down information obtained
through interaction with other agents. The embodied concepts
are constructed to be informative for the robot in terms of its
sensorimotor prediction capability. From that point the effort of
constructing humanlike concepts is shifted towards producing
a translation between the sensorimotor based bottom-up on-
tology and more conventional top-down constructed ontologies.
The suggested framework is based on a parameter free rule
extraction algorithm that successfully has been applied to the
problem of creating finite state descriptions of large, complex
and even chaotic simulated dynamic systems. We will briefly
describe how this algorithm can be ported to an autonomous
robot domain.