Robot oriented state space construction

Hiroshi Ishiguro, Ritsuko Sato, Toru Ishida

Research output: Contribution to conferencePaper

29 Citations (Scopus)

Abstract

The state space of a sensor-based robot in the most previous works has been determined based on human intuitions, however the state space constructed from human viewpoints is not always appropriate for the robot. The robot has a different body, sensors, and tasks, therefore, we consider the robot should have an original internal state space determined based on actions, sensors, and tasks. This paper proposes an approach to construct such a robot oriented state space by statistically analyzing the actions, sensor patterns, and rewards given as results of task executions. In the state space construction, the robot creates sensor pattern classifiers called Empirically Obtained Perceivers (EOPs) the combinations of which represents internal states of the robot. We have confirmed that the robot can construct original state spaces through its vision sensor and achieve navigation tasks with the obtained state spaces in a complicated simulated world.

Original languageEnglish
Pages1496-1501
Number of pages6
Publication statusPublished - 1996 Dec 1
Externally publishedYes
EventProceedings of the 1996 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. Part 3 (of 3) - Osaka, Jpn
Duration: 1996 Nov 41996 Nov 8

Other

OtherProceedings of the 1996 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. Part 3 (of 3)
CityOsaka, Jpn
Period96/11/496/11/8

Fingerprint

Robots
Sensors
Navigation
Classifiers

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Ishiguro, H., Sato, R., & Ishida, T. (1996). Robot oriented state space construction. 1496-1501. Paper presented at Proceedings of the 1996 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. Part 3 (of 3), Osaka, Jpn, .

Robot oriented state space construction. / Ishiguro, Hiroshi; Sato, Ritsuko; Ishida, Toru.

1996. 1496-1501 Paper presented at Proceedings of the 1996 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. Part 3 (of 3), Osaka, Jpn, .

Research output: Contribution to conferencePaper

Ishiguro, H, Sato, R & Ishida, T 1996, 'Robot oriented state space construction' Paper presented at Proceedings of the 1996 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. Part 3 (of 3), Osaka, Jpn, 96/11/4 - 96/11/8, pp. 1496-1501.
Ishiguro H, Sato R, Ishida T. Robot oriented state space construction. 1996. Paper presented at Proceedings of the 1996 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. Part 3 (of 3), Osaka, Jpn, .
Ishiguro, Hiroshi ; Sato, Ritsuko ; Ishida, Toru. / Robot oriented state space construction. Paper presented at Proceedings of the 1996 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. Part 3 (of 3), Osaka, Jpn, .6 p.
@conference{b60bcf6a90b9467da8938a9a16966d90,
title = "Robot oriented state space construction",
abstract = "The state space of a sensor-based robot in the most previous works has been determined based on human intuitions, however the state space constructed from human viewpoints is not always appropriate for the robot. The robot has a different body, sensors, and tasks, therefore, we consider the robot should have an original internal state space determined based on actions, sensors, and tasks. This paper proposes an approach to construct such a robot oriented state space by statistically analyzing the actions, sensor patterns, and rewards given as results of task executions. In the state space construction, the robot creates sensor pattern classifiers called Empirically Obtained Perceivers (EOPs) the combinations of which represents internal states of the robot. We have confirmed that the robot can construct original state spaces through its vision sensor and achieve navigation tasks with the obtained state spaces in a complicated simulated world.",
author = "Hiroshi Ishiguro and Ritsuko Sato and Toru Ishida",
year = "1996",
month = "12",
day = "1",
language = "English",
pages = "1496--1501",
note = "Proceedings of the 1996 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. Part 3 (of 3) ; Conference date: 04-11-1996 Through 08-11-1996",

}

TY - CONF

T1 - Robot oriented state space construction

AU - Ishiguro, Hiroshi

AU - Sato, Ritsuko

AU - Ishida, Toru

PY - 1996/12/1

Y1 - 1996/12/1

N2 - The state space of a sensor-based robot in the most previous works has been determined based on human intuitions, however the state space constructed from human viewpoints is not always appropriate for the robot. The robot has a different body, sensors, and tasks, therefore, we consider the robot should have an original internal state space determined based on actions, sensors, and tasks. This paper proposes an approach to construct such a robot oriented state space by statistically analyzing the actions, sensor patterns, and rewards given as results of task executions. In the state space construction, the robot creates sensor pattern classifiers called Empirically Obtained Perceivers (EOPs) the combinations of which represents internal states of the robot. We have confirmed that the robot can construct original state spaces through its vision sensor and achieve navigation tasks with the obtained state spaces in a complicated simulated world.

AB - The state space of a sensor-based robot in the most previous works has been determined based on human intuitions, however the state space constructed from human viewpoints is not always appropriate for the robot. The robot has a different body, sensors, and tasks, therefore, we consider the robot should have an original internal state space determined based on actions, sensors, and tasks. This paper proposes an approach to construct such a robot oriented state space by statistically analyzing the actions, sensor patterns, and rewards given as results of task executions. In the state space construction, the robot creates sensor pattern classifiers called Empirically Obtained Perceivers (EOPs) the combinations of which represents internal states of the robot. We have confirmed that the robot can construct original state spaces through its vision sensor and achieve navigation tasks with the obtained state spaces in a complicated simulated world.

UR - http://www.scopus.com/inward/record.url?scp=0030393105&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030393105&partnerID=8YFLogxK

M3 - Paper

SP - 1496

EP - 1501

ER -