Automatic path search for roving robot using reinforcement learning

Shigeharu Miyata, Hitomi Nakamura, Akira Yanou, Shin Takehara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Rapid advances in robot technology have been made in recent years. In connection with these advances, robots are expected to be utilized in a variety of places and environments. This study describes 1) a method which allows a robot to measure the location of its destination in the real world based on an image obtained from a single camera, and 2) a method of navigating a robot to a destination which is selected by a user on a display showing the forward robot view. Consideration is also given to cases in which there are obstacles between the robot and the destination. Through the use of reinforcement learning, which is considered a promising candidate among autonomous control techniques, the roving robot tries to find the shortest way to the destination based on information concerning the locations of obstacles and the destination. This study also describes an image-based method of measuring a selected location, the results from a simulation of path finding using reinforcement learning, and the results from an experiment of navigation in a real environment. Finally, a summary of the main conclusions is provided.

Original languageEnglish
Title of host publication2009 4th International Conference on Innovative Computing, Information and Control, ICICIC 2009
Pages169-172
Number of pages4
DOIs
Publication statusPublished - 2009
Event2009 4th International Conference on Innovative Computing, Information and Control, ICICIC 2009 - Kaohsiung, Taiwan, Province of China
Duration: Dec 7 2009Dec 9 2009

Other

Other2009 4th International Conference on Innovative Computing, Information and Control, ICICIC 2009
CountryTaiwan, Province of China
CityKaohsiung
Period12/7/0912/9/09

Fingerprint

Reinforcement learning
Robots
Navigation
Cameras
Display devices

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Software

Cite this

Miyata, S., Nakamura, H., Yanou, A., & Takehara, S. (2009). Automatic path search for roving robot using reinforcement learning. In 2009 4th International Conference on Innovative Computing, Information and Control, ICICIC 2009 (pp. 169-172). [5412489] https://doi.org/10.1109/ICICIC.2009.121

Automatic path search for roving robot using reinforcement learning. / Miyata, Shigeharu; Nakamura, Hitomi; Yanou, Akira; Takehara, Shin.

2009 4th International Conference on Innovative Computing, Information and Control, ICICIC 2009. 2009. p. 169-172 5412489.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Miyata, S, Nakamura, H, Yanou, A & Takehara, S 2009, Automatic path search for roving robot using reinforcement learning. in 2009 4th International Conference on Innovative Computing, Information and Control, ICICIC 2009., 5412489, pp. 169-172, 2009 4th International Conference on Innovative Computing, Information and Control, ICICIC 2009, Kaohsiung, Taiwan, Province of China, 12/7/09. https://doi.org/10.1109/ICICIC.2009.121
Miyata S, Nakamura H, Yanou A, Takehara S. Automatic path search for roving robot using reinforcement learning. In 2009 4th International Conference on Innovative Computing, Information and Control, ICICIC 2009. 2009. p. 169-172. 5412489 https://doi.org/10.1109/ICICIC.2009.121
Miyata, Shigeharu ; Nakamura, Hitomi ; Yanou, Akira ; Takehara, Shin. / Automatic path search for roving robot using reinforcement learning. 2009 4th International Conference on Innovative Computing, Information and Control, ICICIC 2009. 2009. pp. 169-172
@inproceedings{f225ed3c77e54cd0b16e17f70f1dc31c,
title = "Automatic path search for roving robot using reinforcement learning",
abstract = "Rapid advances in robot technology have been made in recent years. In connection with these advances, robots are expected to be utilized in a variety of places and environments. This study describes 1) a method which allows a robot to measure the location of its destination in the real world based on an image obtained from a single camera, and 2) a method of navigating a robot to a destination which is selected by a user on a display showing the forward robot view. Consideration is also given to cases in which there are obstacles between the robot and the destination. Through the use of reinforcement learning, which is considered a promising candidate among autonomous control techniques, the roving robot tries to find the shortest way to the destination based on information concerning the locations of obstacles and the destination. This study also describes an image-based method of measuring a selected location, the results from a simulation of path finding using reinforcement learning, and the results from an experiment of navigation in a real environment. Finally, a summary of the main conclusions is provided.",
author = "Shigeharu Miyata and Hitomi Nakamura and Akira Yanou and Shin Takehara",
year = "2009",
doi = "10.1109/ICICIC.2009.121",
language = "English",
isbn = "9780769538730",
pages = "169--172",
booktitle = "2009 4th International Conference on Innovative Computing, Information and Control, ICICIC 2009",

}

TY - GEN

T1 - Automatic path search for roving robot using reinforcement learning

AU - Miyata, Shigeharu

AU - Nakamura, Hitomi

AU - Yanou, Akira

AU - Takehara, Shin

PY - 2009

Y1 - 2009

N2 - Rapid advances in robot technology have been made in recent years. In connection with these advances, robots are expected to be utilized in a variety of places and environments. This study describes 1) a method which allows a robot to measure the location of its destination in the real world based on an image obtained from a single camera, and 2) a method of navigating a robot to a destination which is selected by a user on a display showing the forward robot view. Consideration is also given to cases in which there are obstacles between the robot and the destination. Through the use of reinforcement learning, which is considered a promising candidate among autonomous control techniques, the roving robot tries to find the shortest way to the destination based on information concerning the locations of obstacles and the destination. This study also describes an image-based method of measuring a selected location, the results from a simulation of path finding using reinforcement learning, and the results from an experiment of navigation in a real environment. Finally, a summary of the main conclusions is provided.

AB - Rapid advances in robot technology have been made in recent years. In connection with these advances, robots are expected to be utilized in a variety of places and environments. This study describes 1) a method which allows a robot to measure the location of its destination in the real world based on an image obtained from a single camera, and 2) a method of navigating a robot to a destination which is selected by a user on a display showing the forward robot view. Consideration is also given to cases in which there are obstacles between the robot and the destination. Through the use of reinforcement learning, which is considered a promising candidate among autonomous control techniques, the roving robot tries to find the shortest way to the destination based on information concerning the locations of obstacles and the destination. This study also describes an image-based method of measuring a selected location, the results from a simulation of path finding using reinforcement learning, and the results from an experiment of navigation in a real environment. Finally, a summary of the main conclusions is provided.

UR - http://www.scopus.com/inward/record.url?scp=77951474941&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951474941&partnerID=8YFLogxK

U2 - 10.1109/ICICIC.2009.121

DO - 10.1109/ICICIC.2009.121

M3 - Conference contribution

AN - SCOPUS:77951474941

SN - 9780769538730

SP - 169

EP - 172

BT - 2009 4th International Conference on Innovative Computing, Information and Control, ICICIC 2009

ER -