Collision-avoidance algorithm for human-symbiotic robot

Yuji Hosoda, Kenjirou Yamamoto, Ryouko Ichinose, Saku Egawa, Junichi Tamamoto, Kouji Tsubouchi, Shinichi Yuta

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

6 Citations (Scopus)

Abstract

A real-time collision-avoidance algorithm for human-symbiotic robots that are required to avoid multiple pedestrians was developed. An algorithm to predict the likelihood of a collision with obstacles was based on the relative velocities between a moving robot and multiple obstacles. An algorithm that can generate the optimum path sequence to a goal in real time was also developed. The collision-avoidance path is generated by repeating an operation to select two tangent paths that connect a via-point on a path to a collision circle of each obstacle that exists in the relative space. A robot - called EMIEW" - using these algorithms with a system for avoiding collisions with many obstacles moves at a speed of 0.8 m/s in a cluster of five people walking at 1.2 m/s. The repeat period for generating a new avoidance path is 0.5s, and the processing time for the developed algorithm in the each period is a maximum of 4 ms.

Original languageEnglish
Title of host publicationICCAS 2010 - International Conference on Control, Automation and Systems
Pages557-561
Number of pages5
Publication statusPublished - 2010
Externally publishedYes
EventInternational Conference on Control, Automation and Systems, ICCAS 2010 - Gyeonggi-do
Duration: 2010 Oct 272010 Oct 30

Other

OtherInternational Conference on Control, Automation and Systems, ICCAS 2010
CityGyeonggi-do
Period10/10/2710/10/30

Fingerprint

Collision avoidance
Robots
Processing

Keywords

  • And obstacle
  • Collision-avoidance
  • Human-symbiotic robot
  • Navigation

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

Hosoda, Y., Yamamoto, K., Ichinose, R., Egawa, S., Tamamoto, J., Tsubouchi, K., & Yuta, S. (2010). Collision-avoidance algorithm for human-symbiotic robot. In ICCAS 2010 - International Conference on Control, Automation and Systems (pp. 557-561). [5669933]

Collision-avoidance algorithm for human-symbiotic robot. / Hosoda, Yuji; Yamamoto, Kenjirou; Ichinose, Ryouko; Egawa, Saku; Tamamoto, Junichi; Tsubouchi, Kouji; Yuta, Shinichi.

ICCAS 2010 - International Conference on Control, Automation and Systems. 2010. p. 557-561 5669933.

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

Hosoda, Y, Yamamoto, K, Ichinose, R, Egawa, S, Tamamoto, J, Tsubouchi, K & Yuta, S 2010, Collision-avoidance algorithm for human-symbiotic robot. in ICCAS 2010 - International Conference on Control, Automation and Systems., 5669933, pp. 557-561, International Conference on Control, Automation and Systems, ICCAS 2010, Gyeonggi-do, 10/10/27.
Hosoda Y, Yamamoto K, Ichinose R, Egawa S, Tamamoto J, Tsubouchi K et al. Collision-avoidance algorithm for human-symbiotic robot. In ICCAS 2010 - International Conference on Control, Automation and Systems. 2010. p. 557-561. 5669933
Hosoda, Yuji ; Yamamoto, Kenjirou ; Ichinose, Ryouko ; Egawa, Saku ; Tamamoto, Junichi ; Tsubouchi, Kouji ; Yuta, Shinichi. / Collision-avoidance algorithm for human-symbiotic robot. ICCAS 2010 - International Conference on Control, Automation and Systems. 2010. pp. 557-561
@inproceedings{e9a40b423a3849f48aa063c42267191d,
title = "Collision-avoidance algorithm for human-symbiotic robot",
abstract = "A real-time collision-avoidance algorithm for human-symbiotic robots that are required to avoid multiple pedestrians was developed. An algorithm to predict the likelihood of a collision with obstacles was based on the relative velocities between a moving robot and multiple obstacles. An algorithm that can generate the optimum path sequence to a goal in real time was also developed. The collision-avoidance path is generated by repeating an operation to select two tangent paths that connect a via-point on a path to a collision circle of each obstacle that exists in the relative space. A robot - called EMIEW{"} - using these algorithms with a system for avoiding collisions with many obstacles moves at a speed of 0.8 m/s in a cluster of five people walking at 1.2 m/s. The repeat period for generating a new avoidance path is 0.5s, and the processing time for the developed algorithm in the each period is a maximum of 4 ms.",
keywords = "And obstacle, Collision-avoidance, Human-symbiotic robot, Navigation",
author = "Yuji Hosoda and Kenjirou Yamamoto and Ryouko Ichinose and Saku Egawa and Junichi Tamamoto and Kouji Tsubouchi and Shinichi Yuta",
year = "2010",
language = "English",
isbn = "9781424474530",
pages = "557--561",
booktitle = "ICCAS 2010 - International Conference on Control, Automation and Systems",

}

TY - GEN

T1 - Collision-avoidance algorithm for human-symbiotic robot

AU - Hosoda, Yuji

AU - Yamamoto, Kenjirou

AU - Ichinose, Ryouko

AU - Egawa, Saku

AU - Tamamoto, Junichi

AU - Tsubouchi, Kouji

AU - Yuta, Shinichi

PY - 2010

Y1 - 2010

N2 - A real-time collision-avoidance algorithm for human-symbiotic robots that are required to avoid multiple pedestrians was developed. An algorithm to predict the likelihood of a collision with obstacles was based on the relative velocities between a moving robot and multiple obstacles. An algorithm that can generate the optimum path sequence to a goal in real time was also developed. The collision-avoidance path is generated by repeating an operation to select two tangent paths that connect a via-point on a path to a collision circle of each obstacle that exists in the relative space. A robot - called EMIEW" - using these algorithms with a system for avoiding collisions with many obstacles moves at a speed of 0.8 m/s in a cluster of five people walking at 1.2 m/s. The repeat period for generating a new avoidance path is 0.5s, and the processing time for the developed algorithm in the each period is a maximum of 4 ms.

AB - A real-time collision-avoidance algorithm for human-symbiotic robots that are required to avoid multiple pedestrians was developed. An algorithm to predict the likelihood of a collision with obstacles was based on the relative velocities between a moving robot and multiple obstacles. An algorithm that can generate the optimum path sequence to a goal in real time was also developed. The collision-avoidance path is generated by repeating an operation to select two tangent paths that connect a via-point on a path to a collision circle of each obstacle that exists in the relative space. A robot - called EMIEW" - using these algorithms with a system for avoiding collisions with many obstacles moves at a speed of 0.8 m/s in a cluster of five people walking at 1.2 m/s. The repeat period for generating a new avoidance path is 0.5s, and the processing time for the developed algorithm in the each period is a maximum of 4 ms.

KW - And obstacle

KW - Collision-avoidance

KW - Human-symbiotic robot

KW - Navigation

UR - http://www.scopus.com/inward/record.url?scp=78751505506&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78751505506&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781424474530

SP - 557

EP - 561

BT - ICCAS 2010 - International Conference on Control, Automation and Systems

ER -