Platform-Independent Benchmarks for Task and Motion Planning

Fabien Lagriffoul; Neil T. Dantam; Caelan Garrett; Aliakbar Akbari; Siddharth Srivastava; Lydia E. Kavraki

doi:10.1109/LRA.2018.2856701

Platform-Independent Benchmarks for Task and Motion Planning

Fabien Lagriffoul, Neil T. Dantam, Caelan Garrett, Aliakbar Akbari, Siddharth Srivastava, Lydia E. Kavraki

Computing and Augmented Intelligence, School of (IAFSE-SCAI)

Research output: Contribution to journal › Article › peer-review

42 Scopus citations

Abstract

We present the first platform-independent evaluation method for task and motion planning (TAMP). Previously point, various problems have been used to test individual planners for specific aspects of TAMP. However, no common set of metrics, formats, and problems have been accepted by the community. We propose a set of benchmark problems covering the challenging aspects of TAMP and a planner-independent specification format for these problems. Our objective is to better evaluate and compare TAMP planners, foster communication, and progress within the field, and lay a foundation to better understand this class of planning problems.

Original language	English (US)
Article number	8411475
Pages (from-to)	3765-3772
Number of pages	8
Journal	IEEE Robotics and Automation Letters
Volume	3
Issue number	4
DOIs	https://doi.org/10.1109/LRA.2018.2856701
State	Published - Oct 2018

Keywords

Performance evaluation and benchmarking
manipulation planning
task planning

ASJC Scopus subject areas

Control and Systems Engineering
Biomedical Engineering
Human-Computer Interaction
Mechanical Engineering
Computer Vision and Pattern Recognition
Computer Science Applications
Control and Optimization
Artificial Intelligence

Access to Document

10.1109/LRA.2018.2856701

Cite this

@article{17de4be72e2a423da26ddee87abda780,

title = "Platform-Independent Benchmarks for Task and Motion Planning",

abstract = "We present the first platform-independent evaluation method for task and motion planning (TAMP). Previously point, various problems have been used to test individual planners for specific aspects of TAMP. However, no common set of metrics, formats, and problems have been accepted by the community. We propose a set of benchmark problems covering the challenging aspects of TAMP and a planner-independent specification format for these problems. Our objective is to better evaluate and compare TAMP planners, foster communication, and progress within the field, and lay a foundation to better understand this class of planning problems.",

keywords = "Performance evaluation and benchmarking, manipulation planning, task planning",

author = "Fabien Lagriffoul and Dantam, {Neil T.} and Caelan Garrett and Aliakbar Akbari and Siddharth Srivastava and Kavraki, {Lydia E.}",

note = "Funding Information: Manuscript received February 24, 2018; accepted June 28, 2018. Date of publication July 16, 2018; date of current version August 8, 2018. This letter was recommended for publication by Associate Editor O. Stasse and Editor N. Tsagarakis upon evaluation of the reviewers{\textquoteright} comments. This work was supported in part by the Swedish Knowledge Foundation (KKS) project “Semantic Robots”, NSF Grants IIS 1317849 and CCF-1514372 to the Kavraki Lab at Rice University, and in part by the Spanish Government through the project DPI2016-80077-R. The work of A. Akbari was supported by the Spanish Government through the Grant FPI 2015. (Corresponding author: Fabien Lagriffoul.) F. Lagriffoul is with the Centre for Applied Autonomous Sensor Systems Lab, {\"O}rebro University, {\"O}rebro SE-701 82, Sweden (e-mail:, Fabien.Lagriffoul@ oru.se). Funding Information: This work was supported in part by the Swedish Knowledge Foundation (KKS) project {"}Semantic Robots{"}, NSF Grants IIS 1317849 and CCF-1514372 to the Kavraki Lab at Rice University, and in part by the Spanish Government through the project DPI2016- 80077-R. The work of A. Akbari was supported by the Spanish Government through the Grant FPI 2015. Publisher Copyright: {\textcopyright} 2016 IEEE.",

year = "2018",

month = oct,

doi = "10.1109/LRA.2018.2856701",

language = "English (US)",

volume = "3",

pages = "3765--3772",

journal = "IEEE Robotics and Automation Letters",

issn = "2377-3766",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "4",

}

TY - JOUR

T1 - Platform-Independent Benchmarks for Task and Motion Planning

AU - Lagriffoul, Fabien

AU - Dantam, Neil T.

AU - Garrett, Caelan

AU - Akbari, Aliakbar

AU - Srivastava, Siddharth

AU - Kavraki, Lydia E.

N1 - Funding Information: Manuscript received February 24, 2018; accepted June 28, 2018. Date of publication July 16, 2018; date of current version August 8, 2018. This letter was recommended for publication by Associate Editor O. Stasse and Editor N. Tsagarakis upon evaluation of the reviewers’ comments. This work was supported in part by the Swedish Knowledge Foundation (KKS) project “Semantic Robots”, NSF Grants IIS 1317849 and CCF-1514372 to the Kavraki Lab at Rice University, and in part by the Spanish Government through the project DPI2016-80077-R. The work of A. Akbari was supported by the Spanish Government through the Grant FPI 2015. (Corresponding author: Fabien Lagriffoul.) F. Lagriffoul is with the Centre for Applied Autonomous Sensor Systems Lab, Örebro University, Örebro SE-701 82, Sweden (e-mail:, Fabien.Lagriffoul@ oru.se). Funding Information: This work was supported in part by the Swedish Knowledge Foundation (KKS) project "Semantic Robots", NSF Grants IIS 1317849 and CCF-1514372 to the Kavraki Lab at Rice University, and in part by the Spanish Government through the project DPI2016- 80077-R. The work of A. Akbari was supported by the Spanish Government through the Grant FPI 2015. Publisher Copyright: © 2016 IEEE.

PY - 2018/10

Y1 - 2018/10

N2 - We present the first platform-independent evaluation method for task and motion planning (TAMP). Previously point, various problems have been used to test individual planners for specific aspects of TAMP. However, no common set of metrics, formats, and problems have been accepted by the community. We propose a set of benchmark problems covering the challenging aspects of TAMP and a planner-independent specification format for these problems. Our objective is to better evaluate and compare TAMP planners, foster communication, and progress within the field, and lay a foundation to better understand this class of planning problems.

AB - We present the first platform-independent evaluation method for task and motion planning (TAMP). Previously point, various problems have been used to test individual planners for specific aspects of TAMP. However, no common set of metrics, formats, and problems have been accepted by the community. We propose a set of benchmark problems covering the challenging aspects of TAMP and a planner-independent specification format for these problems. Our objective is to better evaluate and compare TAMP planners, foster communication, and progress within the field, and lay a foundation to better understand this class of planning problems.

KW - Performance evaluation and benchmarking

KW - manipulation planning

KW - task planning

UR - http://www.scopus.com/inward/record.url?scp=85063307661&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063307661&partnerID=8YFLogxK

U2 - 10.1109/LRA.2018.2856701

DO - 10.1109/LRA.2018.2856701

M3 - Article

AN - SCOPUS:85063307661

SN - 2377-3766

VL - 3

SP - 3765

EP - 3772

JO - IEEE Robotics and Automation Letters

JF - IEEE Robotics and Automation Letters

IS - 4

M1 - 8411475

ER -

Platform-Independent Benchmarks for Task and Motion Planning

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this