---
title: "Towards a Model of Grounded Concept Formation"
authors:
  - "Stefan Wrobel"
doi: ""
url: "https://ijcai.org/proceedings/1991/104"
pdf: "https://ijcai.org/proceedings/1991/0104.pdf"
venue: "Proceedings of the Twelfth International Joint Conference on Artificial Intelligence"
year: 1991
pages: "712-718"
track: "Learning Be Knowledge Acquisition"
keywords:
---

# Towards a Model of Grounded Concept Formation

Stefan Wrobel

*Proceedings of the Twelfth International Joint Conference on Artificial Intelligence*, pages 712-718.

## Abstract

In most research on concept formation within machine learning and cognitive psychology, the f ea tures from which concepts are built are assumed to be provided as elementary vocabulary. In this paper, we argue that this is an unnecessarily limited paradigm within which to examine concept formation. Based on evidence from psychology and machine learning, we contend that a principled account of the origin of features can only be given with a grounded model of concept formation, i.e ., with a model that incorporates direct access to the world via sensors and manipulators. We discuss the domain of process control as a suitable framework for research into such models , and present a first approach to the problem of developing elementary vocabularies from perceptual sensor data.