International Workshop on Ontologies for Autonomous Robotics (ROBONTICS 2020) @ FOIS 2020, part of Bolzano Summer of Knowledge (BOSK 2020), Sept. 13, Bolzano, Italy

WORKSHOP SCOPE AND AIM

ROBONTICS 2020 is the first edition of a workshop aimed at providing a platform to disseminate research into robot autonomy enabled by knowledge-driven approaches, and in particular formal ontologies. Its purpose is to foster communication between the fields of robotics, ontology, and knowledge representation and reasoning, to match open problems to promising approaches, and to review progress in knowledge-driven robotics.

Ontologies are a well-established technique for knowledge representation and management. They formalize conceptualizations at a symbolic, communicable level, allowing re-use of knowledge items between different modules or even agents, as well as explaining reasoning-based decisions. Ontologies have already seen use in robotics, and standardization efforts for robotics knowledge management are in progress.

Nevertheless, many hard problems remain in robotics, especially involving autonomous robotic agents operating in natural or human environments. Many research projects, motivated by applications in healthcare assistance, logistics, autonomous driving etc, aim to bring robots out of the lab and into realistic human environments. One of the difficulties frustrating such efforts is the large amount of real-world knowledge that an agent needs to have to be able to act competently and autonomously. Further, any item of knowledge is often relevant for many agents and behaviors, and as such should be reusable. To garner trust and enable debugging, knowledge should also be accessible to human operators, both in terms of explaining what knowledge is present in a system, as well as providing ways to easily amend it if necessary.

It would then seem there are still application areas to explore in robotics, and in particular autonomous robotics, for knowledge-enabled and formalized knowledge representation approaches. We are at a point where we can look at previous applications of ontology engineering in robotics to glean lessons from experience, and to consider new knowledge representation and reasoning approaches for new, and even harder problems.

IMPORTANT DATES

  • Submission deadline: June 29, 2020
  • Review notification: July 27, 2020
  • Camera ready: August 17, 2020
  • Workshop: September 13 (half day)

LIST OF TOPICS

Participants are invited to submit original short papers (from 4 to 6 pages + references) for oral presentation, on topics such as:

  • Foundational issues:
    • are there some ontological approaches better suited than others for autonomous robotics? why?
    • how should we ontologically model notions like capability, action, interaction, context etc. in robotics?
  • Robustness:
    • how can ontologies be used to help robots cope with the variety and relatively fluid structure of human environments?
  • Ontologies in the perception-action loop:
    • what roles can ontology play in autonomous manipulation?
    • how can we help robots autonomously cope with manipulation problems using ontology?
    • how can ontology be used to support machine learning for object classification?
  • Interactivity:
    • how can knowledge about other agents present in the environment be modelled?
    • how should we ontologically model the flow of an interaction, such as a conversation or shared task?
  • Normed behavior:
    • how should we ontologically represent, and then have a robot act according to, norms on behavior such as cultural expectations?
    • how can these expectations be acquired, and would they be the same for robots as they are for humans?
  • Explainability:
    • decision chains are very complex; how can these be organized and presented at various levels of detail for the benefit of a human user?
    • what, ontologically, is an explanation? what is a good explanation, and how can one be generated from a collection of knowledge items?

WORKSHOP CO-CHAIRS

  • Stefano Borgo, Laboratory for Applied Ontology (LOA), ISTC CNR, Trento, Italy
  • Aldo Gangemi, University of Bologna and ISTC-CNR, Italy
  • Robert Porzel, Digital Media Lab, University of Bremen, Germany
  • Daniel Beßler, Institute for Artificial Intelligence, University of Bremen, Germany
  • Mihai Pomarlan, Faculty of Linguistics and Literature, University of Bremen, Germany
  • Mohammed Diab, Institute of Industrial and Control Engineering, Universitat Politècnica de Catalunya, Barcelona, Spain
  • Alberto Olivares-Alarcos, Institut de Robòtica i Informàtica Industrial (CSIC-UPC), Barcelona, Spain

SUBMISSION INFORMATION

Papers presenting initial or ongoing research are welcome; so are position papers delineating robotics problems and/or discussing the suitability of knowlege engineering approaches to solve such problems.

All the contributions to the workshop must be submitted according to the IOS press format available from https://www.iospress.nl/service/authors/latex-and-word-tools-for-book-authors/. Submitted papers must not exceed 6 pages (not including references).

Papers will be refereed and accepted on the basis of their scientific merit, originality, and relevance to the workshop. Each paper will be reviewed by two Program Committee members.

Papers must be submitted electronically in PDF, using this link:

PUBLICATION

Accepted contributions to the workshop will be published in an open access CEUR volume as part of the new IAOA series (see http://ceur-ws.org/iaoa.html).

(Banner image is provided by Françoise Foliot to wikimedia commons under the CC-BY-SA 4.0 license.)