TENANT

Tool fostEriNg Ai plaNning in roboTics

Stand-Alone version

Table of Contents

• Table of Contents
• About The Project
  • Built With
• Getting Started
  • Prerequisites
  • Installation and Run

About The Project

TENANT (Tool fostEriNg Ai plaNning in roboTics) is a knowledge engineering software tool that facilitates domain experts in the definition of a complete representation of the specific production knowledge of a whole manufactoring shop-floor. In particular, it can be used to define goals, tasks and a set operational constraints of a production process.

Built With

Getting Started

In TENANT, the knowledge base definition process consists of several modeling steps shown in the figure below.

The representation framework behind TENANT relies on a state-of-the-art ontology called SOHO (Sharework Ontology for Human-Robot Collaboration) expanded with some concepts from OPIS, a language defined for describing manufacturing processes.

Prerequisites

• A linux distribution (Ubuntu 18.04 has been used for running and testing the software)
• Python 3 and pip
• Virtualenv (not required but recommended)

Installation and Run

In order to run the software, follow the instructions below

1. Clone the repo and move into the folder

   git clone https://github.com/pstlab/TENANT_sa.git
   cd ./TENANT_sa

2. Create a virtual environment with virtualenv and activate it (only if you want use virtualenv)

   python3 -m pip install virtualenv
   python3 -m venv env
   source ./env/bin/activate

   • To deactivate the virtual environment use the command deactivate
3. Install the requirements contained in requirements.txt

   python3 -m pip install -r ./requirements.txt

4. To fill the database with toy scenarios, run (not required)

   python3 ./init_db.py
   # or
   python3 ./init_cembre.py

5. To initialize operator functions with a set of functions common in manufacturing scenarios, run (not required)

   python3 ./taxonomy_functions.py

6. Run the server

   python3 ./run.py

A local server will be started at http://127.0.0.1:5000/. Open this address with any browser to use the software.

(back to top)