TP-ONT

A Task-Planning Ontology

Setup Instructions

Create and activate a virtual environment:

python3 -m venv .venv
source .venv/bin/activate

Install required packages:

python3 -m pip install -r requirements.txt

For KG Construction

sudo apt install libxcb-cursor-dev

For OntoAligner

Download nltk required data:

python3 -m pip install nltk

In Python:

import nltk
nltk.download('averaged_perceptron_tagger_eng')

Running instructions

KG Construction

To create the KG, you can use the bash script to run multiple domains at once, or the Python PDDLKGConstructor.py directly.

Ontology Construction

Once you have created the KG, you can use extract_tbox_from_kg.py to extract the ontology from the knowledge graph.

Adding plans

Sample plan instances can be found in here. In order to generate more plans and simulations, please follow the steps below.

Prerequisites

To create plans and state simulations, you need to install the FastDownward planner and VAL.

Running instructions

If you would like to generate new plans, or plan simulations, you can use the RunFDPlanner.py file to run the planner and state simulator, or the run_planner.sh to run multiple domains in a row.