Evolutionary trajectory learning for autonomous robots by means of geometric approximations of polygonal obstacles

M. M.A. Hashem; Keigo Watanabe; Kiyotaka Izumi

Evolutionary trajectory learning for autonomous robots by means of geometric approximations of polygonal obstacles

M. M.A. Hashem, Keigo Watanabe, Kiyotaka Izumi

Research output: Contribution to journal › Conference article › peer-review

Abstract

This paper addresses the issue of flexible geometric approximations of polygonal obstacles for Intelligent Autonomous Robot (IAR) navigation which is the extension of our previous work. The trajectory learning problem for IAR navigation is formulated as a constrained discrete-time-optimal control problem where the polygonal obstacles are the constraints. From the visibility and sensor modeling concepts, polygonal obstacles within the environment are approximated as either by circles or by ellipses depending on the shape and size of them. Furthermore, some practical issues are identified and resolved through these type of approximations. The effectiveness of these methods is illustrated by some simulations of the robot within a heavily obstacle environment.

Original language	English
Pages (from-to)	II-734 - II-739
Journal	Proceedings of the IEEE International Conference on Systems, Man and Cybernetics
Volume	2
Publication status	Published - Dec 1 1999
Externally published	Yes
Event	1999 IEEE International Conference on Systems, Man, and Cybernetics 'Human Communication and Cybernetics' - Tokyo, Jpn Duration: Oct 12 1999 → Oct 15 1999

ASJC Scopus subject areas

Control and Systems Engineering
Hardware and Architecture

Cite this

Evolutionary trajectory learning for autonomous robots by means of geometric approximations of polygonal obstacles. / Hashem, M. M.A.; Watanabe, Keigo; Izumi, Kiyotaka.
In: Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, Vol. 2, 01.12.1999, p. II-734 - II-739.

Research output: Contribution to journal › Conference article › peer-review

@article{b4e2dd4391fc4d73b4eb7e1662140f7e,

title = "Evolutionary trajectory learning for autonomous robots by means of geometric approximations of polygonal obstacles",

abstract = "This paper addresses the issue of flexible geometric approximations of polygonal obstacles for Intelligent Autonomous Robot (IAR) navigation which is the extension of our previous work. The trajectory learning problem for IAR navigation is formulated as a constrained discrete-time-optimal control problem where the polygonal obstacles are the constraints. From the visibility and sensor modeling concepts, polygonal obstacles within the environment are approximated as either by circles or by ellipses depending on the shape and size of them. Furthermore, some practical issues are identified and resolved through these type of approximations. The effectiveness of these methods is illustrated by some simulations of the robot within a heavily obstacle environment.",

author = "Hashem, {M. M.A.} and Keigo Watanabe and Kiyotaka Izumi",

year = "1999",

month = dec,

day = "1",

language = "English",

volume = "2",

pages = "II--734 -- II--739",

journal = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",

issn = "0884-3627",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "1999 IEEE International Conference on Systems, Man, and Cybernetics 'Human Communication and Cybernetics' ; Conference date: 12-10-1999 Through 15-10-1999",

}

TY - JOUR

T1 - Evolutionary trajectory learning for autonomous robots by means of geometric approximations of polygonal obstacles

AU - Hashem, M. M.A.

AU - Watanabe, Keigo

AU - Izumi, Kiyotaka

PY - 1999/12/1

Y1 - 1999/12/1

N2 - This paper addresses the issue of flexible geometric approximations of polygonal obstacles for Intelligent Autonomous Robot (IAR) navigation which is the extension of our previous work. The trajectory learning problem for IAR navigation is formulated as a constrained discrete-time-optimal control problem where the polygonal obstacles are the constraints. From the visibility and sensor modeling concepts, polygonal obstacles within the environment are approximated as either by circles or by ellipses depending on the shape and size of them. Furthermore, some practical issues are identified and resolved through these type of approximations. The effectiveness of these methods is illustrated by some simulations of the robot within a heavily obstacle environment.

AB - This paper addresses the issue of flexible geometric approximations of polygonal obstacles for Intelligent Autonomous Robot (IAR) navigation which is the extension of our previous work. The trajectory learning problem for IAR navigation is formulated as a constrained discrete-time-optimal control problem where the polygonal obstacles are the constraints. From the visibility and sensor modeling concepts, polygonal obstacles within the environment are approximated as either by circles or by ellipses depending on the shape and size of them. Furthermore, some practical issues are identified and resolved through these type of approximations. The effectiveness of these methods is illustrated by some simulations of the robot within a heavily obstacle environment.

UR - http://www.scopus.com/inward/record.url?scp=0033307717&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033307717&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0033307717

SN - 0884-3627

VL - 2

SP - II-734 - II-739

JO - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

JF - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

T2 - 1999 IEEE International Conference on Systems, Man, and Cybernetics 'Human Communication and Cybernetics'

Y2 - 12 October 1999 through 15 October 1999

ER -

Evolutionary trajectory learning for autonomous robots by means of geometric approximations of polygonal obstacles

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this