Grounding Mundane Inference in Perception

Ian D Horswill

doi:10.1023/A:1008865025943

Grounding Mundane Inference in Perception

Ian D Horswill^*

^*Corresponding author for this work

Computer Science

Research output: Contribution to journal › Article › peer-review

8 Scopus citations

Abstract

We describe a uniform technique for representing both sensory data and the attentional state of an agent using a subset of modal logic with indexicals. The resulting representation maps naturally into feed-forward parallel networks or can be implemented on stock hardware using bit-mask instructions. The representation has "circuit-semantics" (Nilsson, 1994, Rosenschein and Kaelbling, 1986), but can efficiently represent propositions containing modals, unary predicates, and functions. We describe an example using Kludge, a vision-based mobile robot programmed to perform simple natural language instructions involving fetching and following tasks.

Original language	English (US)
Pages (from-to)	63-77
Number of pages	15
Journal	Autonomous Robots
Volume	5
Issue number	1
DOIs	https://doi.org/10.1023/A:1008865025943
State	Published - 1998

Keywords

Active perception
Agent architectures
Knowledge representation
Reasoning
Vision

ASJC Scopus subject areas

Artificial Intelligence

Access to Document

10.1023/A:1008865025943

Fingerprint Dive into the research topics of 'Grounding Mundane Inference in Perception'. Together they form a unique fingerprint.

Cite this

@article{77775706c214446ba725be0d4b886f9d,

title = "Grounding Mundane Inference in Perception",

abstract = "We describe a uniform technique for representing both sensory data and the attentional state of an agent using a subset of modal logic with indexicals. The resulting representation maps naturally into feed-forward parallel networks or can be implemented on stock hardware using bit-mask instructions. The representation has {"}circuit-semantics{"} (Nilsson, 1994, Rosenschein and Kaelbling, 1986), but can efficiently represent propositions containing modals, unary predicates, and functions. We describe an example using Kludge, a vision-based mobile robot programmed to perform simple natural language instructions involving fetching and following tasks.",

keywords = "Active perception, Agent architectures, Knowledge representation, Reasoning, Vision",

author = "Horswill, {Ian D}",

note = "Funding Information: Many thanks to Leslie Kaelbling, Lars Bergstrom, and Ivan Yen, for providing useful comments on this paper. Support for this research was provided in part by the National Science Foundation under grant number IRI–9625041. The Institute for the Learning Sciences was established in 1989 with the support of Anderson Consulting, part of the Arthur Anderson Worldwide Organization. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.",

year = "1998",

doi = "10.1023/A:1008865025943",

language = "English (US)",

volume = "5",

pages = "63--77",

journal = "Autonomous Robots",

issn = "0929-5593",

publisher = "Springer Netherlands",

number = "1",

}

TY - JOUR

T1 - Grounding Mundane Inference in Perception

AU - Horswill, Ian D

N1 - Funding Information: Many thanks to Leslie Kaelbling, Lars Bergstrom, and Ivan Yen, for providing useful comments on this paper. Support for this research was provided in part by the National Science Foundation under grant number IRI–9625041. The Institute for the Learning Sciences was established in 1989 with the support of Anderson Consulting, part of the Arthur Anderson Worldwide Organization. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.

PY - 1998

Y1 - 1998

N2 - We describe a uniform technique for representing both sensory data and the attentional state of an agent using a subset of modal logic with indexicals. The resulting representation maps naturally into feed-forward parallel networks or can be implemented on stock hardware using bit-mask instructions. The representation has "circuit-semantics" (Nilsson, 1994, Rosenschein and Kaelbling, 1986), but can efficiently represent propositions containing modals, unary predicates, and functions. We describe an example using Kludge, a vision-based mobile robot programmed to perform simple natural language instructions involving fetching and following tasks.

AB - We describe a uniform technique for representing both sensory data and the attentional state of an agent using a subset of modal logic with indexicals. The resulting representation maps naturally into feed-forward parallel networks or can be implemented on stock hardware using bit-mask instructions. The representation has "circuit-semantics" (Nilsson, 1994, Rosenschein and Kaelbling, 1986), but can efficiently represent propositions containing modals, unary predicates, and functions. We describe an example using Kludge, a vision-based mobile robot programmed to perform simple natural language instructions involving fetching and following tasks.

KW - Active perception

KW - Agent architectures

KW - Knowledge representation

KW - Reasoning

KW - Vision

UR - http://www.scopus.com/inward/record.url?scp=0032022543&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032022543&partnerID=8YFLogxK

U2 - 10.1023/A:1008865025943

DO - 10.1023/A:1008865025943

M3 - Article

AN - SCOPUS:0032022543

VL - 5

SP - 63

EP - 77

JO - Autonomous Robots

JF - Autonomous Robots

SN - 0929-5593

IS - 1

ER -

Grounding Mundane Inference in Perception

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this