Acquisition and propagation of spatial constraints based on qualitative information

Takushi Sogo, Hiroshi Ishiguro, Toru Ishida

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

In robot navigation, one of the important and fundamental issues is to find positions of landmarks or vision sensors located around the robot. This paper proposes a method for reconstructing qualitative positions of multiple vision sensors from qualitative information observed by the vision sensors, i.e., motion directions of moving objects. In order to directly acquire the qualitative positions of points, the method proposed in this paper iterates the following steps: 1) observing motion directions (left or right) of moving objects with the vision sensors, 2) classifying the vision sensors into spatially classified pairs based on the motion directions, 3) acquiring three point constraints, and 4) propagating the constraints. Compared with the previous methods, which reconstruct the environment structure from quantitative measurements and acquire qualitative representations by abstracting it, this paper focuses on how to acquire qualitative positions of landmarks from low-level, simple, and reliable information (that is, "qualitative"). The method been evaluated with simulations and also verified with observation errors.

Original languageEnglish
Pages (from-to)268-278
Number of pages11
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume23
Issue number3
DOIs
Publication statusPublished - 2001 Mar 1
Externally publishedYes

Fingerprint

Propagation
Sensors
Sensor
Landmarks
Moving Objects
Motion
Robots
Observed Information
Robot Navigation
Iterate
Navigation
Acquisition
Robot
Vision
Simulation

Keywords

  • Constraint propagation
  • Map building
  • Qualitative observation
  • Qualitative spatial representation
  • Spatially classified pair
  • Three point constraint

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Cite this

Acquisition and propagation of spatial constraints based on qualitative information. / Sogo, Takushi; Ishiguro, Hiroshi; Ishida, Toru.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, No. 3, 01.03.2001, p. 268-278.

Research output: Contribution to journalArticle

@article{928fa32fe9ea43faa3bfb6e0adc5bee4,
title = "Acquisition and propagation of spatial constraints based on qualitative information",
abstract = "In robot navigation, one of the important and fundamental issues is to find positions of landmarks or vision sensors located around the robot. This paper proposes a method for reconstructing qualitative positions of multiple vision sensors from qualitative information observed by the vision sensors, i.e., motion directions of moving objects. In order to directly acquire the qualitative positions of points, the method proposed in this paper iterates the following steps: 1) observing motion directions (left or right) of moving objects with the vision sensors, 2) classifying the vision sensors into spatially classified pairs based on the motion directions, 3) acquiring three point constraints, and 4) propagating the constraints. Compared with the previous methods, which reconstruct the environment structure from quantitative measurements and acquire qualitative representations by abstracting it, this paper focuses on how to acquire qualitative positions of landmarks from low-level, simple, and reliable information (that is, {"}qualitative{"}). The method been evaluated with simulations and also verified with observation errors.",
keywords = "Constraint propagation, Map building, Qualitative observation, Qualitative spatial representation, Spatially classified pair, Three point constraint",
author = "Takushi Sogo and Hiroshi Ishiguro and Toru Ishida",
year = "2001",
month = "3",
day = "1",
doi = "10.1109/34.910879",
language = "English",
volume = "23",
pages = "268--278",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "3",

}

TY - JOUR

T1 - Acquisition and propagation of spatial constraints based on qualitative information

AU - Sogo, Takushi

AU - Ishiguro, Hiroshi

AU - Ishida, Toru

PY - 2001/3/1

Y1 - 2001/3/1

N2 - In robot navigation, one of the important and fundamental issues is to find positions of landmarks or vision sensors located around the robot. This paper proposes a method for reconstructing qualitative positions of multiple vision sensors from qualitative information observed by the vision sensors, i.e., motion directions of moving objects. In order to directly acquire the qualitative positions of points, the method proposed in this paper iterates the following steps: 1) observing motion directions (left or right) of moving objects with the vision sensors, 2) classifying the vision sensors into spatially classified pairs based on the motion directions, 3) acquiring three point constraints, and 4) propagating the constraints. Compared with the previous methods, which reconstruct the environment structure from quantitative measurements and acquire qualitative representations by abstracting it, this paper focuses on how to acquire qualitative positions of landmarks from low-level, simple, and reliable information (that is, "qualitative"). The method been evaluated with simulations and also verified with observation errors.

AB - In robot navigation, one of the important and fundamental issues is to find positions of landmarks or vision sensors located around the robot. This paper proposes a method for reconstructing qualitative positions of multiple vision sensors from qualitative information observed by the vision sensors, i.e., motion directions of moving objects. In order to directly acquire the qualitative positions of points, the method proposed in this paper iterates the following steps: 1) observing motion directions (left or right) of moving objects with the vision sensors, 2) classifying the vision sensors into spatially classified pairs based on the motion directions, 3) acquiring three point constraints, and 4) propagating the constraints. Compared with the previous methods, which reconstruct the environment structure from quantitative measurements and acquire qualitative representations by abstracting it, this paper focuses on how to acquire qualitative positions of landmarks from low-level, simple, and reliable information (that is, "qualitative"). The method been evaluated with simulations and also verified with observation errors.

KW - Constraint propagation

KW - Map building

KW - Qualitative observation

KW - Qualitative spatial representation

KW - Spatially classified pair

KW - Three point constraint

UR - http://www.scopus.com/inward/record.url?scp=0035280074&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035280074&partnerID=8YFLogxK

U2 - 10.1109/34.910879

DO - 10.1109/34.910879

M3 - Article

AN - SCOPUS:0035280074

VL - 23

SP - 268

EP - 278

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 3

ER -