Emergent intentionality in perception-action subsumption hierarchies

Windridge, David ORCID: https://orcid.org/0000-0001-5507-8516 (2017) Emergent intentionality in perception-action subsumption hierarchies. Frontiers in Robotics and AI, 4 , 38. ISSN 2296-9144 (doi:10.3389/frobt.2017.00038)

[img]
Preview
PDF - Published version (with publisher's formatting)
Available under License Creative Commons Attribution.

Download (158kB) | Preview
[img]
Preview
PDF - Final accepted version (with author's formatting)
Download (891kB) | Preview

Abstract

A cognitively-autonomous artificial agent may be defined as one able to modify both its external world-model and the framework by which it represents the world, requiring two simultaneous optimization objectives. This presents deep epistemological issues centered on the question of how a framework for representation (as opposed to the entities it represents) may be objectively validated. In this summary paper, formalizing previous work in this field, it is argued that subsumptive perception-action learning has the capacity to resolve these issues by {\em a)} building the perceptual hierarchy from the bottom up so as to ground all proposed representations and {\em b)} maintaining a bijective coupling between proposed percepts and projected action possibilities to ensure empirical falsifiability of these grounded representations. In doing so, we will show that such subsumptive perception-action learners intrinsically incorporate a model for how intentionality emerges from randomized exploratory activity in the form of 'motor babbling'. Moreover, such a model of intentionality also naturally translates into a model for human-computer interfacing that makes minimal assumptions as to cognitive states.

Item Type: Article
Additional Information: Article number = 38
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 22394
Notes on copyright: Copyright: © 2017 Windridge.
Useful Links:
Depositing User: David Windridge
Date Deposited: 23 Aug 2017 14:32
Last Modified: 05 Aug 2020 07:47
URI: https://eprints.mdx.ac.uk/id/eprint/22394

Actions (login required)

Edit Item Edit Item