Egocentric qualitative spatial knowledge representation for physical robots

T. Wagner, Ubbo E Visser, O. Herzog

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Although recent (physical) robots have powerful sensors and actuators their abilities to show intelligent behavior is often limited, One key reason is the lack of an appropriate spatial representation. Spatial knowledge plays a crucial role in navigation, (self- and object-)localization, planning and reasoning for physically grounded robots. However, it is a major difficulty of most existing approaches that each of these tasks imposes heterogeneous requirements on the representation. In this paper, we propose an egocentric representation which relies on ID ordering information that still provides sufficient allocentric information to solve navigation and (self- and object-)localization tasks. Furthermore, we claim that our approach supports an efficient, incremental process based on a simple 1D-representation.

Original languageEnglish (US)
Pages (from-to)25-42
Number of pages18
JournalRobotics and Autonomous Systems
Volume49
Issue number1-2 SPEC. ISS.
DOIs
StatePublished - Nov 30 2004
Externally publishedYes

Fingerprint

Knowledge representation
Knowledge Representation
Navigation
Robot
Robots
Actuator
Actuators
Reasoning
Planning
Sufficient
Sensor
Requirements
Sensors
Object
Knowledge

Keywords

  • Qualitative knowledge representation
  • Qualitative navigation

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Computational Mechanics

Cite this

Egocentric qualitative spatial knowledge representation for physical robots. / Wagner, T.; Visser, Ubbo E; Herzog, O.

In: Robotics and Autonomous Systems, Vol. 49, No. 1-2 SPEC. ISS., 30.11.2004, p. 25-42.

Research output: Contribution to journalArticle

@article{003657b8758e4ad8b1f007a0938fa427,
title = "Egocentric qualitative spatial knowledge representation for physical robots",
abstract = "Although recent (physical) robots have powerful sensors and actuators their abilities to show intelligent behavior is often limited, One key reason is the lack of an appropriate spatial representation. Spatial knowledge plays a crucial role in navigation, (self- and object-)localization, planning and reasoning for physically grounded robots. However, it is a major difficulty of most existing approaches that each of these tasks imposes heterogeneous requirements on the representation. In this paper, we propose an egocentric representation which relies on ID ordering information that still provides sufficient allocentric information to solve navigation and (self- and object-)localization tasks. Furthermore, we claim that our approach supports an efficient, incremental process based on a simple 1D-representation.",
keywords = "Qualitative knowledge representation, Qualitative navigation",
author = "T. Wagner and Visser, {Ubbo E} and O. Herzog",
year = "2004",
month = "11",
day = "30",
doi = "10.1016/j.robot.2004.07.022",
language = "English (US)",
volume = "49",
pages = "25--42",
journal = "Robotics and Autonomous Systems",
issn = "0921-8890",
publisher = "Elsevier",
number = "1-2 SPEC. ISS.",

}

TY - JOUR

T1 - Egocentric qualitative spatial knowledge representation for physical robots

AU - Wagner, T.

AU - Visser, Ubbo E

AU - Herzog, O.

PY - 2004/11/30

Y1 - 2004/11/30

N2 - Although recent (physical) robots have powerful sensors and actuators their abilities to show intelligent behavior is often limited, One key reason is the lack of an appropriate spatial representation. Spatial knowledge plays a crucial role in navigation, (self- and object-)localization, planning and reasoning for physically grounded robots. However, it is a major difficulty of most existing approaches that each of these tasks imposes heterogeneous requirements on the representation. In this paper, we propose an egocentric representation which relies on ID ordering information that still provides sufficient allocentric information to solve navigation and (self- and object-)localization tasks. Furthermore, we claim that our approach supports an efficient, incremental process based on a simple 1D-representation.

AB - Although recent (physical) robots have powerful sensors and actuators their abilities to show intelligent behavior is often limited, One key reason is the lack of an appropriate spatial representation. Spatial knowledge plays a crucial role in navigation, (self- and object-)localization, planning and reasoning for physically grounded robots. However, it is a major difficulty of most existing approaches that each of these tasks imposes heterogeneous requirements on the representation. In this paper, we propose an egocentric representation which relies on ID ordering information that still provides sufficient allocentric information to solve navigation and (self- and object-)localization tasks. Furthermore, we claim that our approach supports an efficient, incremental process based on a simple 1D-representation.

KW - Qualitative knowledge representation

KW - Qualitative navigation

UR - http://www.scopus.com/inward/record.url?scp=8344270864&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=8344270864&partnerID=8YFLogxK

U2 - 10.1016/j.robot.2004.07.022

DO - 10.1016/j.robot.2004.07.022

M3 - Article

VL - 49

SP - 25

EP - 42

JO - Robotics and Autonomous Systems

JF - Robotics and Autonomous Systems

SN - 0921-8890

IS - 1-2 SPEC. ISS.

ER -