Integration of constraint logic programming and artificial neural networks for driving robots

Koichiro Ishikawa; Tsutomu Fujinami; Akito Sakurai

Integration of constraint logic programming and artificial neural networks for driving robots

Koichiro Ishikawa, Tsutomu Fujinami, Akito Sakurai

Research output: Contribution to conference › Paper › peer-review

Abstract

We propose a robot architecture to integrate symbolic and non-symbolic information processings. Artificial neural networks (ANN) are quick, flexible and robust. Symbolic processing is on the other hand comprehensible, effective, controllable, and consistent. To integrate symbolic and non-symbolic methods, we consider the relation between a robot and its environment as constraints. To describe and solve such constraints we turn to Constraint Logic Programming (CLP). To construct a robot that works in the complex environment, CLP and ANN are integrated into a unified framework such that CLP evaluates the behavior candidates proposed by ANN according to the constraints and ANN learns adequate behavior according to evaluations by CLP. We implemented the decision process in our robot that drove through a test course as we expected.

Original language	English
Pages	1011-1016
Number of pages	6
Publication status	Published - 2001
Externally published	Yes
Event	2001 IEEE/RSJ International Conference on Intelligent Robots and Systems - Maui, HI, United States Duration: 2001 Oct 29 → 2001 Nov 3

Other

Other	2001 IEEE/RSJ International Conference on Intelligent Robots and Systems
Country/Territory	United States
City	Maui, HI
Period	01/10/29 → 01/11/3

ASJC Scopus subject areas

Control and Systems Engineering
Software
Computer Vision and Pattern Recognition
Computer Science Applications

Cite this

@conference{65b802dd778441749f5a3175bf3e5411,

title = "Integration of constraint logic programming and artificial neural networks for driving robots",

abstract = "We propose a robot architecture to integrate symbolic and non-symbolic information processings. Artificial neural networks (ANN) are quick, flexible and robust. Symbolic processing is on the other hand comprehensible, effective, controllable, and consistent. To integrate symbolic and non-symbolic methods, we consider the relation between a robot and its environment as constraints. To describe and solve such constraints we turn to Constraint Logic Programming (CLP). To construct a robot that works in the complex environment, CLP and ANN are integrated into a unified framework such that CLP evaluates the behavior candidates proposed by ANN according to the constraints and ANN learns adequate behavior according to evaluations by CLP. We implemented the decision process in our robot that drove through a test course as we expected.",

author = "Koichiro Ishikawa and Tsutomu Fujinami and Akito Sakurai",

year = "2001",

language = "English",

pages = "1011--1016",

note = "2001 IEEE/RSJ International Conference on Intelligent Robots and Systems ; Conference date: 29-10-2001 Through 03-11-2001",

}

TY - CONF

T1 - Integration of constraint logic programming and artificial neural networks for driving robots

AU - Ishikawa, Koichiro

AU - Fujinami, Tsutomu

AU - Sakurai, Akito

PY - 2001

Y1 - 2001

N2 - We propose a robot architecture to integrate symbolic and non-symbolic information processings. Artificial neural networks (ANN) are quick, flexible and robust. Symbolic processing is on the other hand comprehensible, effective, controllable, and consistent. To integrate symbolic and non-symbolic methods, we consider the relation between a robot and its environment as constraints. To describe and solve such constraints we turn to Constraint Logic Programming (CLP). To construct a robot that works in the complex environment, CLP and ANN are integrated into a unified framework such that CLP evaluates the behavior candidates proposed by ANN according to the constraints and ANN learns adequate behavior according to evaluations by CLP. We implemented the decision process in our robot that drove through a test course as we expected.

AB - We propose a robot architecture to integrate symbolic and non-symbolic information processings. Artificial neural networks (ANN) are quick, flexible and robust. Symbolic processing is on the other hand comprehensible, effective, controllable, and consistent. To integrate symbolic and non-symbolic methods, we consider the relation between a robot and its environment as constraints. To describe and solve such constraints we turn to Constraint Logic Programming (CLP). To construct a robot that works in the complex environment, CLP and ANN are integrated into a unified framework such that CLP evaluates the behavior candidates proposed by ANN according to the constraints and ANN learns adequate behavior according to evaluations by CLP. We implemented the decision process in our robot that drove through a test course as we expected.

UR - http://www.scopus.com/inward/record.url?scp=0035557989&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035557989&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0035557989

SP - 1011

EP - 1016

T2 - 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems

Y2 - 29 October 2001 through 3 November 2001

ER -

Integration of constraint logic programming and artificial neural networks for driving robots

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this