Automated Planning Techniques for Robot Manipulation Tasks Involving Articulated Objects

Alessio Capitanelli, Marco Maratea, Fulvio Matrogiovanni, Mauro Vallati

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

2 Citations (Scopus)

Abstract

The goal-oriented manipulation of articulated objects plays an important role in real-world robot tasks. Current approaches typically pose a number of simplifying assumptions to reason upon how to obtain an articulated object’s goal configuration, and exploit ad hoc algorithms. The consequence is two-fold: firstly, it is difficult to generalise obtained solutions (in terms of actions a robot can execute) to different target object’s configurations and, in a broad sense, to different object’s physical characteristics; secondly, the representation and the reasoning layers are tightly coupled and inter-dependent.

In this paper we investigate the use of automated planning techniques for dealing with articulated objects manipulation tasks. Such techniques allow for a clear separation between knowledge and reasoning, as advocated in Knowledge Engineering. We introduce two PDDL formulations of the task, which rely on conceptually different representations of the orientation of the objects. Experiments involving several planners and increasing size objects demonstrate the effectiveness of the proposed models, and confirm its exploitability when embedded in a real-world robot software architecture.
LanguageEnglish
Title of host publicationAI*IA 2017 Advances in Artificial Intelligence
Subtitle of host publicationXVIth International Conference of the Italian Association for Artificial Intelligence, Bari, Italy, November 14-17, 2017, Proceedings.
PublisherSpringer Verlag
Pages483-497
Number of pages15
ISBN (Electronic)9783319701691
ISBN (Print)9783319701684
DOIs
Publication statusPublished - 7 Nov 2017
Event16th International Conference of the Italian Association for Artificial Intelligence - University of Bari, Bari, Italy
Duration: 14 Nov 201717 Nov 2017
Conference number: 16
http://aiia2017.di.uniba.it/ (Link to Conference Website)

Publication series

NameLecture Notes in Artificial Intelligence
PublisherSpringer

Conference

Conference16th International Conference of the Italian Association for Artificial Intelligence
Abbreviated titleAI*IA 2017
CountryItaly
CityBari
Period14/11/1717/11/17
Internet address

Fingerprint

Robots
Planning
Knowledge engineering
Software architecture
Experiments

Cite this

Capitanelli, A., Maratea, M., Matrogiovanni, F., & Vallati, M. (2017). Automated Planning Techniques for Robot Manipulation Tasks Involving Articulated Objects. In AI*IA 2017 Advances in Artificial Intelligence: XVIth International Conference of the Italian Association for Artificial Intelligence, Bari, Italy, November 14-17, 2017, Proceedings. (pp. 483-497). (Lecture Notes in Artificial Intelligence). Springer Verlag. https://doi.org/10.1007/978-3-319-70169-1_36
Capitanelli, Alessio ; Maratea, Marco ; Matrogiovanni, Fulvio ; Vallati, Mauro. / Automated Planning Techniques for Robot Manipulation Tasks Involving Articulated Objects. AI*IA 2017 Advances in Artificial Intelligence: XVIth International Conference of the Italian Association for Artificial Intelligence, Bari, Italy, November 14-17, 2017, Proceedings.. Springer Verlag, 2017. pp. 483-497 (Lecture Notes in Artificial Intelligence).
@inproceedings{7a18317b096a48879bbf7ba1427781fd,
title = "Automated Planning Techniques for Robot Manipulation Tasks Involving Articulated Objects",
abstract = "The goal-oriented manipulation of articulated objects plays an important role in real-world robot tasks. Current approaches typically pose a number of simplifying assumptions to reason upon how to obtain an articulated object’s goal configuration, and exploit ad hoc algorithms. The consequence is two-fold: firstly, it is difficult to generalise obtained solutions (in terms of actions a robot can execute) to different target object’s configurations and, in a broad sense, to different object’s physical characteristics; secondly, the representation and the reasoning layers are tightly coupled and inter-dependent.In this paper we investigate the use of automated planning techniques for dealing with articulated objects manipulation tasks. Such techniques allow for a clear separation between knowledge and reasoning, as advocated in Knowledge Engineering. We introduce two PDDL formulations of the task, which rely on conceptually different representations of the orientation of the objects. Experiments involving several planners and increasing size objects demonstrate the effectiveness of the proposed models, and confirm its exploitability when embedded in a real-world robot software architecture.",
author = "Alessio Capitanelli and Marco Maratea and Fulvio Matrogiovanni and Mauro Vallati",
year = "2017",
month = "11",
day = "7",
doi = "10.1007/978-3-319-70169-1_36",
language = "English",
isbn = "9783319701684",
series = "Lecture Notes in Artificial Intelligence",
publisher = "Springer Verlag",
pages = "483--497",
booktitle = "AI*IA 2017 Advances in Artificial Intelligence",

}

Capitanelli, A, Maratea, M, Matrogiovanni, F & Vallati, M 2017, Automated Planning Techniques for Robot Manipulation Tasks Involving Articulated Objects. in AI*IA 2017 Advances in Artificial Intelligence: XVIth International Conference of the Italian Association for Artificial Intelligence, Bari, Italy, November 14-17, 2017, Proceedings.. Lecture Notes in Artificial Intelligence, Springer Verlag, pp. 483-497, 16th International Conference of the Italian Association for Artificial Intelligence, Bari, Italy, 14/11/17. https://doi.org/10.1007/978-3-319-70169-1_36

Automated Planning Techniques for Robot Manipulation Tasks Involving Articulated Objects. / Capitanelli, Alessio; Maratea, Marco; Matrogiovanni, Fulvio; Vallati, Mauro.

AI*IA 2017 Advances in Artificial Intelligence: XVIth International Conference of the Italian Association for Artificial Intelligence, Bari, Italy, November 14-17, 2017, Proceedings.. Springer Verlag, 2017. p. 483-497 (Lecture Notes in Artificial Intelligence).

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

TY - GEN

T1 - Automated Planning Techniques for Robot Manipulation Tasks Involving Articulated Objects

AU - Capitanelli, Alessio

AU - Maratea, Marco

AU - Matrogiovanni, Fulvio

AU - Vallati, Mauro

PY - 2017/11/7

Y1 - 2017/11/7

N2 - The goal-oriented manipulation of articulated objects plays an important role in real-world robot tasks. Current approaches typically pose a number of simplifying assumptions to reason upon how to obtain an articulated object’s goal configuration, and exploit ad hoc algorithms. The consequence is two-fold: firstly, it is difficult to generalise obtained solutions (in terms of actions a robot can execute) to different target object’s configurations and, in a broad sense, to different object’s physical characteristics; secondly, the representation and the reasoning layers are tightly coupled and inter-dependent.In this paper we investigate the use of automated planning techniques for dealing with articulated objects manipulation tasks. Such techniques allow for a clear separation between knowledge and reasoning, as advocated in Knowledge Engineering. We introduce two PDDL formulations of the task, which rely on conceptually different representations of the orientation of the objects. Experiments involving several planners and increasing size objects demonstrate the effectiveness of the proposed models, and confirm its exploitability when embedded in a real-world robot software architecture.

AB - The goal-oriented manipulation of articulated objects plays an important role in real-world robot tasks. Current approaches typically pose a number of simplifying assumptions to reason upon how to obtain an articulated object’s goal configuration, and exploit ad hoc algorithms. The consequence is two-fold: firstly, it is difficult to generalise obtained solutions (in terms of actions a robot can execute) to different target object’s configurations and, in a broad sense, to different object’s physical characteristics; secondly, the representation and the reasoning layers are tightly coupled and inter-dependent.In this paper we investigate the use of automated planning techniques for dealing with articulated objects manipulation tasks. Such techniques allow for a clear separation between knowledge and reasoning, as advocated in Knowledge Engineering. We introduce two PDDL formulations of the task, which rely on conceptually different representations of the orientation of the objects. Experiments involving several planners and increasing size objects demonstrate the effectiveness of the proposed models, and confirm its exploitability when embedded in a real-world robot software architecture.

UR - http://aiia2017.di.uniba.it/index.php/accepted-papers/

UR - http://www.springer.com/series/1244

U2 - 10.1007/978-3-319-70169-1_36

DO - 10.1007/978-3-319-70169-1_36

M3 - Conference contribution

SN - 9783319701684

T3 - Lecture Notes in Artificial Intelligence

SP - 483

EP - 497

BT - AI*IA 2017 Advances in Artificial Intelligence

PB - Springer Verlag

ER -

Capitanelli A, Maratea M, Matrogiovanni F, Vallati M. Automated Planning Techniques for Robot Manipulation Tasks Involving Articulated Objects. In AI*IA 2017 Advances in Artificial Intelligence: XVIth International Conference of the Italian Association for Artificial Intelligence, Bari, Italy, November 14-17, 2017, Proceedings.. Springer Verlag. 2017. p. 483-497. (Lecture Notes in Artificial Intelligence). https://doi.org/10.1007/978-3-319-70169-1_36