Towards a Theory of Awareness at ICAART 2024

At the ICAART 2024 Conference in Rome we had a Special Session organized by Luc Steels on the Awareness Inside topic funded by the EIC Pathfinder programme.

In the session I presented the initial developments towards a theory of awareness that the ASLab team is doing inside the CORESENSE and METATOOL projects.

We did a short, ten minute presentation, and after that we had an interesting conversation around the ideas presented and the possibility of developing a complete model-based theory of aware agents.

The presentation addressed the possibility of having a solid theory of awareness both for humans and machines and what are the elements that such a theory should have. We talked about two of these elements: the clear delimitation of a domain of phenomena, and the essential concepts that are the cornerstones of the theory.

These were the concepts that we proposed/discussed:

  • Sensing: The production of information for the subject from an object.
  • Perceiving: The integration of the sensory information bound to an object into a model of the object.
  • Model: Integrated actionable representation; an information structure that sustains a modelling relation.
  • Engine: Set of operations over a model.
  • Inference: Derive conclusions from the model. Apply engines to model.
  • Valid inference: A inference whose result matches the phenomenon at the modelled object.
  • Exert a model: Perform valid inferences from the model.
  • Understanding: Achieving exertability of a model of the object/environment.
  • Specific understanding: Understanding concerning a specific set of exertions.
  • Mission understanding: Understanding concerning a set of mission-bound exertions.
  • Omega understanding: Understanding all possible exertions of a model in relation to an object.
  • Awareness: Real-time understanding of sensory flows.
  • Self-awareness: Subject-bound awareness. Awareness concerning inner perception.

Get the complete presentation:

And the paper:

AI for Conscious Machines

November 14, 2013

The many challenges of Artificial Intelligence. November 13-15 2023

A workshop to evaluate the challenges and repercussions of the “new” Artificial Intelligence (AI) taking place at Residencia La Cristalera, Miraflores de la Sierra (Madrid).

It has been organized by Juan Poyatos (CNB), Juan Rodríguez (IIIA), and David Ríos (ICMAT) abd sponsored by AIHub-CSIC and the AXA Research Fund.


There I gave a talk on machine consciousness based on our current activity in the Horizon Europe projects CORESENSE and METATOOL.

DARPA Workshop on Self-Aware Machines

In 2004, DARPA and John McCarthy organised a Workshop on Self-Aware Computing Systems because the topic of artificial self-awareness was gaining momentum. It was a workshop by invitation at Washington D.C. Most participants came from USA, but there were two from Europe: Aaron Sloman from UK and Ricardo Sanz from Spain.

Sanz, Hayes, Minsky at DARPA Workshop on Self-Aware Computing Systems.

These were the thirty-three participants in the workshop:

Aaron SlomanEyal AmirPush Singh
Bernard BaarsJames Van OverscheldeRaghu Ramakrishnan
Brian WilliamsJohn McCarthyRicardo Sanz
Greg SullivanKen ForbusRichard Scherl
Danny BobrowTom HinrichsRichard Gabriel
Markus FromhertzLen SchubertRichard Thomason
Deborah McGuinnessLokendra ShastriRobert Stroud
Drew McDermottMichael CoxSheila McIlraith
Don PerlisMichael WhitbrockStan Franklin
Mike AndersonMike AndersonStuart Shapiro
Tim OatesOwen HollandYaron Shlomi
DARPA Worksop participants.

During three days we discussed the possibilities and approaches to machine self-awareness, within the specific pespective of artificial intelligence. Twenty years after, the discussion remains at the same point. Not much advance has been produced

Maybe the problem is too difficult for human minds.

Singularidad Tecnológica

Evento sobre la Singularidad Tecnológica organizado por la Sección de Pensamiento Marginal del Ateneo de Madrid en 2021.

PRESENTA: Brígida de Fez Algarra
INTRODUCE: José Luis Cordeiro
MODERA: Lola Marcos

PONENTES:
Antonio Miguel Carmona, PhD (Economía) Profesor de Economía, Oficial del Ejército del Aire (RV) y Político
Gabriel Vázquez Torres, Ingeniero Informático, MSc (c) Experto en Data Science e Inteligencia Artificial
Ricardo Sanz, PhD (Ingeniería) Profesor e Investigador de la Universidad Politécnica de Madrid

Lógica y Terminators

La inteligencia artificial es una tecnología muy relevante y de gran impacto potencial en la industria y la sociedad. En esta charla se comentaron algunos de los principales temas que sirvieron de base para un debate con los futuros ingenieros industriales de UPM ETSII. Una conferencia pronunciada dentro del ciclo de conferencias Hazte Industrial.

La versión PDF de las diapositivas de la charla se puede descargar desde aquí.

The Self Beyond Humans

I will give a talk titled The Self Beyond Humans at Reykjavik University on May 16, 2013. The talk addresses the issue of the construction of the self from the perspective of machine consciousness.

Many current research trends point toward a technology of robot selfhood. The pursuit of selves for machines is motivated from a desire to equip robots with sophisticated human-like competences. Self and self-awareness constitute one of the cornerstones of consciousness, a whimsically peculiar aspect of our humanhood. While humans are the best “ground truth” we have in this respect, the best example to inspect and imitate, anthropomorphism is a procrustean path that shall be followed with care. Many attempts to create artificial selves are based on a shallow replication of biological behavioral traits; a true engineering technology of robot selves, however, must be based on a rigorous theory of consciousness, beyond humans.

A scientific, general theory of consciousness should be much more than just some “scientific progress towards understanding how consciousness can emerge form the activity of neurons and their interactions”. While the human brain is our best source of information about consciousness, the construction of a universal, general theory of consciousness is hampered by the almost absolute and excessive focus on the human brain, human cognition, and human neurophysiology. Human brains should not be the only systems we consider in work; a general theory should address at least the many other systems of interest: other kinds of animals, machines, and even social groups. In this talk I will address the emergence of a theoretical framework for Self Beyond Humans. This theoretical framework shall eventually lead to technological assets for robot selfhood to enable them to properly operate in ecological, medical, technical and economic terms in a variety of circumstances. A positive theory of self shall be centered on system functional architecture, sidetracking philosophical discussions on the nature of ‘content and self’ and leveraging the value of concrete topologies and measurements.

Future robots will have selves that may be enormously alien to humans; but, in a very precise sense, they will be quite similar to ours but with a deeper, purer essence, devoid of all that noise produced by biological evolution.