TP-ONT: An Ontology for Enhanced Reasoning in AI Task Planning via Atomic Decomposition

TY - CHAP

T1 - TP-ONT

T2 - An Ontology for Enhanced Reasoning in AI Task Planning via Atomic Decomposition

AU - Armony, Ma'ayan

AU - Meroño-Peñuela, Albert

AU - Canal, Gerard

PY - 2026/7/16

Y1 - 2026/7/16

N2 - AI planning involves finding a sequence of actions that achieve a predefined goal when executed from a given initial state of the environment. Task planning is used to execute tasks specified in formal planning description languages. Ontologies to support the planning process have mainly been used in robotics; however, existing ontologies rarely provide direct mappings between planning constructs and semantic representations, and they typically do not decompose planning terms into their constituent elements. This limits expressive querying, task analysis across environments, and the integration of external knowledge. In this paper, we present TP-ONT, a novel ontology for task planning designed to address these shortcomings. TP-ONT decomposes states and predicates into their atomic components and incorporates object type hierarchies, enabling richer reasoning over relations between specified environments, actions, states, and plans. Our framework for knowledge graph and ontology construction allows automatic extension from new planning descriptions, as well as new plan solutions. Evaluation using 18 competency questions shows that the baseline ontologies can answer at most 7 questions partially or fully, whereas TP-ONT is able to answer all questions.

AB - AI planning involves finding a sequence of actions that achieve a predefined goal when executed from a given initial state of the environment. Task planning is used to execute tasks specified in formal planning description languages. Ontologies to support the planning process have mainly been used in robotics; however, existing ontologies rarely provide direct mappings between planning constructs and semantic representations, and they typically do not decompose planning terms into their constituent elements. This limits expressive querying, task analysis across environments, and the integration of external knowledge. In this paper, we present TP-ONT, a novel ontology for task planning designed to address these shortcomings. TP-ONT decomposes states and predicates into their atomic components and incorporates object type hierarchies, enabling richer reasoning over relations between specified environments, actions, states, and plans. Our framework for knowledge graph and ontology construction allows automatic extension from new planning descriptions, as well as new plan solutions. Evaluation using 18 competency questions shows that the baseline ontologies can answer at most 7 questions partially or fully, whereas TP-ONT is able to answer all questions.

M3 - Conference paper

BT - The Semantic Web – ISWC 2026

ER -