ORIGAMI - Ontology-based engineeRInG for plAnning in ManufacturIng (DUS.AD016.149)

Area tematica

Scienze umane e sociali, patrimonio culturale

Area progettuale

Struttura responsabile del progetto di ricerca

Istituto di scienze e tecnologie della cognizione (ISTC)

Responsabile di progetto

ALESSANDRO UMBRICO
Telefono: 0644595223
E-mail: alessandro.umbrico@istc.cnr.it

Abstract

The deployment of Human-Robot Collaborative Robots (i.e., cobots) in manufacturing (HRC)
requires addressing multiple challenges. It is of paramount importance to endow cobots with
the ability of quickly adapting their behaviours to the actual state of the environment and to
keep the user safe and engaged during the interaction. Long-term research activities are
ongoing to enable robots to autonomously operate in environments, i.e., understanding the
actual situation, planning their tasks and acting to safely and effectively achieve some given
goals [1]. Several approaches aim at achieving robust action selection via Artificial
Intelligence (AI) Planning or robust execution via some form of finite state machine (FSM)
[2,3].
Although automated planning technologies have shown promising results in real-world
scenarios [4,5,6], a widespread use of them is still far from being achieved. A key limiting
factor for the diffusion of these technologies is their ``usability" and a lack of Knowledge
Engineering tools for planning systems [7].

Obiettivi

The development of tools that facilitate the integration (and interaction) of AI planning and
robotics entails different skills that are all necessary to effectively address the underlying
variety of control issues, spanning from low-level control to decisional (and behavioral)
autonomy.
Domain experts are usually not familiar with those technologies. They may not have the
technical skills needed to synthesize models that effectively represent and solve addressed
problems. There is also a ``language gap" between what a domain expert wants to represent
and how this can be represented via a planning specification. Not to mention the specific
features of the different planning technologies that may represent and reason about different
domain elements, constraints and abstraction levels. A crucial knowledge engineering
problem is thus the lack of a generally accepted modeling methodology entailing many
potential back-and-forth (re)work over models and control parameters before defining the
proper control configuration.

Data inizio attività

01/10/2021

Parole chiave

Timeline-based Planning and Scheduling, Knowledge Engineering, Human-Robot Collaboration

Ultimo aggiornamento: 20/05/2024