HTN planning for pick-and-place manipulation

Hisashi Hayashi, Hideki Ogawa, Nobuto Matsuhira

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

1 Citation (Scopus)

Abstract

We introduce new heuristics of HTN (Hierarchical Task Network) planning for mobile robots with two arms/hands that pick and place objects among movable obstacles. Based on our new heuristics, the robot moves obstacles if necessary, picks and places the target objects without collisions. The robot chooses the (right or left) hand to use for each manipulation in order to avoid collisions and reduce the number of obstacle movements. In most of the previous approaches that combine task planning and motion planning, collisions between an arm and obstacles are checked only by the lower-level geometric motion planner. Therefore, the high-level general-purpose task planner often produces a plan that is not executable by the lower-level modules. On the other hand, in our new heuristics, the task planner roughly checks collisions, and produces executable plans.

Original languageEnglish
Title of host publicationICAART 2013 - Proceedings of the 5th International Conference on Agents and Artificial Intelligence
PublisherSciTePress
Pages383-388
Number of pages6
Volume1
ISBN (Print)9789898565389
Publication statusPublished - 2013
Event5th International Conference on Agents and Artificial Intelligence, ICAART 2013 - Barcelona
Duration: 2013 Feb 152013 Feb 18

Other

Other5th International Conference on Agents and Artificial Intelligence, ICAART 2013
CityBarcelona
Period13/2/1513/2/18

Fingerprint

End effectors
Robots
Planning
Motion planning
Mobile robots

Keywords

  • HTN planning
  • Manipulation
  • Robot

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Hayashi, H., Ogawa, H., & Matsuhira, N. (2013). HTN planning for pick-and-place manipulation. In ICAART 2013 - Proceedings of the 5th International Conference on Agents and Artificial Intelligence (Vol. 1, pp. 383-388). SciTePress.

HTN planning for pick-and-place manipulation. / Hayashi, Hisashi; Ogawa, Hideki; Matsuhira, Nobuto.

ICAART 2013 - Proceedings of the 5th International Conference on Agents and Artificial Intelligence. Vol. 1 SciTePress, 2013. p. 383-388.

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

Hayashi, H, Ogawa, H & Matsuhira, N 2013, HTN planning for pick-and-place manipulation. in ICAART 2013 - Proceedings of the 5th International Conference on Agents and Artificial Intelligence. vol. 1, SciTePress, pp. 383-388, 5th International Conference on Agents and Artificial Intelligence, ICAART 2013, Barcelona, 13/2/15.
Hayashi H, Ogawa H, Matsuhira N. HTN planning for pick-and-place manipulation. In ICAART 2013 - Proceedings of the 5th International Conference on Agents and Artificial Intelligence. Vol. 1. SciTePress. 2013. p. 383-388
Hayashi, Hisashi ; Ogawa, Hideki ; Matsuhira, Nobuto. / HTN planning for pick-and-place manipulation. ICAART 2013 - Proceedings of the 5th International Conference on Agents and Artificial Intelligence. Vol. 1 SciTePress, 2013. pp. 383-388
@inproceedings{9f10702bdf444b0d9e225e8cad5daa95,
title = "HTN planning for pick-and-place manipulation",
abstract = "We introduce new heuristics of HTN (Hierarchical Task Network) planning for mobile robots with two arms/hands that pick and place objects among movable obstacles. Based on our new heuristics, the robot moves obstacles if necessary, picks and places the target objects without collisions. The robot chooses the (right or left) hand to use for each manipulation in order to avoid collisions and reduce the number of obstacle movements. In most of the previous approaches that combine task planning and motion planning, collisions between an arm and obstacles are checked only by the lower-level geometric motion planner. Therefore, the high-level general-purpose task planner often produces a plan that is not executable by the lower-level modules. On the other hand, in our new heuristics, the task planner roughly checks collisions, and produces executable plans.",
keywords = "HTN planning, Manipulation, Robot",
author = "Hisashi Hayashi and Hideki Ogawa and Nobuto Matsuhira",
year = "2013",
language = "English",
isbn = "9789898565389",
volume = "1",
pages = "383--388",
booktitle = "ICAART 2013 - Proceedings of the 5th International Conference on Agents and Artificial Intelligence",
publisher = "SciTePress",

}

TY - GEN

T1 - HTN planning for pick-and-place manipulation

AU - Hayashi, Hisashi

AU - Ogawa, Hideki

AU - Matsuhira, Nobuto

PY - 2013

Y1 - 2013

N2 - We introduce new heuristics of HTN (Hierarchical Task Network) planning for mobile robots with two arms/hands that pick and place objects among movable obstacles. Based on our new heuristics, the robot moves obstacles if necessary, picks and places the target objects without collisions. The robot chooses the (right or left) hand to use for each manipulation in order to avoid collisions and reduce the number of obstacle movements. In most of the previous approaches that combine task planning and motion planning, collisions between an arm and obstacles are checked only by the lower-level geometric motion planner. Therefore, the high-level general-purpose task planner often produces a plan that is not executable by the lower-level modules. On the other hand, in our new heuristics, the task planner roughly checks collisions, and produces executable plans.

AB - We introduce new heuristics of HTN (Hierarchical Task Network) planning for mobile robots with two arms/hands that pick and place objects among movable obstacles. Based on our new heuristics, the robot moves obstacles if necessary, picks and places the target objects without collisions. The robot chooses the (right or left) hand to use for each manipulation in order to avoid collisions and reduce the number of obstacle movements. In most of the previous approaches that combine task planning and motion planning, collisions between an arm and obstacles are checked only by the lower-level geometric motion planner. Therefore, the high-level general-purpose task planner often produces a plan that is not executable by the lower-level modules. On the other hand, in our new heuristics, the task planner roughly checks collisions, and produces executable plans.

KW - HTN planning

KW - Manipulation

KW - Robot

UR - http://www.scopus.com/inward/record.url?scp=84877958504&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877958504&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84877958504

SN - 9789898565389

VL - 1

SP - 383

EP - 388

BT - ICAART 2013 - Proceedings of the 5th International Conference on Agents and Artificial Intelligence

PB - SciTePress

ER -