Dynamically extending planning models using an ontology

Michael Cashmore, Maria Fox, Derek Long, Daniele Magazzeni, Bram Ridder, Valerio De Carolis, David Lane, Francesco Maurelli

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

Abstract

In this paper we couple a deterministic planner with an ontology, in order to adapt to new discoveries during plan execution and to reason about the affordances that are available to the planner as the set of known objects is updated. This allows us to extend the planning agent’s functionality during execution. We use as an example planning for persistent autonomous behaviour in underwater vehicles. Planning in this scenario takes place in a symbolic model of the environment, simulating sequences of possible decisions. Ensuring that the simulation remains robust requires careful matching of the model to the real world, including dynamically updating the model from continuous sensing actions. We describe how our system constructs an initial state for planning, using the ontology; how the ontology is also used to determine the results of each action performed by the planner; and finally demonstrate the performance of the system in a simulation, in which two AUVs are required to cooperate in an unknown environment, demonstrating that with additional reasoning the planning system is able to make new efficient choices, taking advantage of the environment in new ways.
LanguageEnglish
Title of host publicationProceedings of the 2nd ICAPS Workshop on Planning and Robotics (PlanRob)
EditorsAlberto Finzi, Felix Ingrand, Andrea Orlandini
Place of Publication[Jerusalem]
Pages79-85
Number of pages7
Publication statusPublished - 8 Jun 2015

Fingerprint

Ontology
Planning

Keywords

  • AI planning
  • ontologies
  • autonomous underwater vehicles (AUVs)
  • artificial intelligence

Cite this

Cashmore, M., Fox, M., Long, D., Magazzeni, D., Ridder, B., De Carolis, V., ... Maurelli, F. (2015). Dynamically extending planning models using an ontology. In A. Finzi, F. Ingrand, & A. Orlandini (Eds.), Proceedings of the 2nd ICAPS Workshop on Planning and Robotics (PlanRob) (pp. 79-85). [Jerusalem].
Cashmore, Michael ; Fox, Maria ; Long, Derek ; Magazzeni, Daniele ; Ridder, Bram ; De Carolis, Valerio ; Lane, David ; Maurelli, Francesco. / Dynamically extending planning models using an ontology. Proceedings of the 2nd ICAPS Workshop on Planning and Robotics (PlanRob). editor / Alberto Finzi ; Felix Ingrand ; Andrea Orlandini. [Jerusalem], 2015. pp. 79-85
@inproceedings{172d8fa8972947be8ea344059d27d464,
title = "Dynamically extending planning models using an ontology",
abstract = "In this paper we couple a deterministic planner with an ontology, in order to adapt to new discoveries during plan execution and to reason about the affordances that are available to the planner as the set of known objects is updated. This allows us to extend the planning agent’s functionality during execution. We use as an example planning for persistent autonomous behaviour in underwater vehicles. Planning in this scenario takes place in a symbolic model of the environment, simulating sequences of possible decisions. Ensuring that the simulation remains robust requires careful matching of the model to the real world, including dynamically updating the model from continuous sensing actions. We describe how our system constructs an initial state for planning, using the ontology; how the ontology is also used to determine the results of each action performed by the planner; and finally demonstrate the performance of the system in a simulation, in which two AUVs are required to cooperate in an unknown environment, demonstrating that with additional reasoning the planning system is able to make new efficient choices, taking advantage of the environment in new ways.",
keywords = "AI planning, ontologies, autonomous underwater vehicles (AUVs), artificial intelligence",
author = "Michael Cashmore and Maria Fox and Derek Long and Daniele Magazzeni and Bram Ridder and {De Carolis}, Valerio and David Lane and Francesco Maurelli",
year = "2015",
month = "6",
day = "8",
language = "English",
pages = "79--85",
editor = "Alberto Finzi and Felix Ingrand and Andrea Orlandini",
booktitle = "Proceedings of the 2nd ICAPS Workshop on Planning and Robotics (PlanRob)",

}

Cashmore, M, Fox, M, Long, D, Magazzeni, D, Ridder, B, De Carolis, V, Lane, D & Maurelli, F 2015, Dynamically extending planning models using an ontology. in A Finzi, F Ingrand & A Orlandini (eds), Proceedings of the 2nd ICAPS Workshop on Planning and Robotics (PlanRob). [Jerusalem], pp. 79-85.

Dynamically extending planning models using an ontology. / Cashmore, Michael; Fox, Maria; Long, Derek; Magazzeni, Daniele; Ridder, Bram; De Carolis, Valerio; Lane, David; Maurelli, Francesco.

Proceedings of the 2nd ICAPS Workshop on Planning and Robotics (PlanRob). ed. / Alberto Finzi; Felix Ingrand; Andrea Orlandini. [Jerusalem], 2015. p. 79-85.

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

TY - GEN

T1 - Dynamically extending planning models using an ontology

AU - Cashmore, Michael

AU - Fox, Maria

AU - Long, Derek

AU - Magazzeni, Daniele

AU - Ridder, Bram

AU - De Carolis, Valerio

AU - Lane, David

AU - Maurelli, Francesco

PY - 2015/6/8

Y1 - 2015/6/8

N2 - In this paper we couple a deterministic planner with an ontology, in order to adapt to new discoveries during plan execution and to reason about the affordances that are available to the planner as the set of known objects is updated. This allows us to extend the planning agent’s functionality during execution. We use as an example planning for persistent autonomous behaviour in underwater vehicles. Planning in this scenario takes place in a symbolic model of the environment, simulating sequences of possible decisions. Ensuring that the simulation remains robust requires careful matching of the model to the real world, including dynamically updating the model from continuous sensing actions. We describe how our system constructs an initial state for planning, using the ontology; how the ontology is also used to determine the results of each action performed by the planner; and finally demonstrate the performance of the system in a simulation, in which two AUVs are required to cooperate in an unknown environment, demonstrating that with additional reasoning the planning system is able to make new efficient choices, taking advantage of the environment in new ways.

AB - In this paper we couple a deterministic planner with an ontology, in order to adapt to new discoveries during plan execution and to reason about the affordances that are available to the planner as the set of known objects is updated. This allows us to extend the planning agent’s functionality during execution. We use as an example planning for persistent autonomous behaviour in underwater vehicles. Planning in this scenario takes place in a symbolic model of the environment, simulating sequences of possible decisions. Ensuring that the simulation remains robust requires careful matching of the model to the real world, including dynamically updating the model from continuous sensing actions. We describe how our system constructs an initial state for planning, using the ontology; how the ontology is also used to determine the results of each action performed by the planner; and finally demonstrate the performance of the system in a simulation, in which two AUVs are required to cooperate in an unknown environment, demonstrating that with additional reasoning the planning system is able to make new efficient choices, taking advantage of the environment in new ways.

KW - AI planning

KW - ontologies

KW - autonomous underwater vehicles (AUVs)

KW - artificial intelligence

M3 - Conference contribution book

SP - 79

EP - 85

BT - Proceedings of the 2nd ICAPS Workshop on Planning and Robotics (PlanRob)

A2 - Finzi, Alberto

A2 - Ingrand, Felix

A2 - Orlandini, Andrea

CY - [Jerusalem]

ER -

Cashmore M, Fox M, Long D, Magazzeni D, Ridder B, De Carolis V et al. Dynamically extending planning models using an ontology. In Finzi A, Ingrand F, Orlandini A, editors, Proceedings of the 2nd ICAPS Workshop on Planning and Robotics (PlanRob). [Jerusalem]. 2015. p. 79-85