General Intelligence in Embodied Agents

conference session on General Intelligence in Embodied Agents, as part of an IEEE Symposium on Human-Level AI
WHEN/WHERE : 15 Mon -19 Fri April 2013, Singapore
PAPER SUBMISSION DEADLINE: December 12 (12-12-12, midnight GMT), no further extensions
Please join us in Singapore April 2013 for presentations and discussions on general intelligence, embodiment and human-level AI!
This Special Session on General Intelligence in Embodied Agents is part of the IEEE Symposium on Computational Intelligence for Human-like Intelligence, which in turn is part of the IEEE Symposium Series on Computational Intelligence,
(to find the Special Session on that page, scroll down till you see “CIHLI 2013, IEEE Symposium on Computational Intelligence for Human-like Intelligence” and click on that link).
If your research touches human-level AI but not embodiment specifically, you may want to submit to the IEEE Symposium on Computational Intelligence for Human-like Intelligence, of which this Special Session is a part.


One critical aspect of human-like intelligence is the capability to control bodies in the pursuit of a variety of human-like goals in environments, especially environments resembling the everyday human world.   The achievement of this capability may be pursued via robotics, or via embodying synthetic intelligent software in virtual agents in virtual worlds such as 3D videogame-like worlds.   Controlling embodied agents carrying out a variety of complex goals in complex environments is a difficult problem, requiring robust generalization and transfer learning ability, and practical creativity.   Confronting this problem places various sorts of stringent requirements on the underlying computational intelligence system, which different architectures may seek to fulfill in different ways.
The focus of this special session is on how architectures designed with artificial general intelligence in mind, cope with the challenges involved in achieving goals involving controlling bodies in worlds, especially worlds bearing some resemblance to the everyday human world.
This Special Session is open to contributions on any topic directly related to the interfacing between artificial general intelligence architectures and the problem of controlling bodies in worlds resembling the everyday human world.   Contributions presenting empirical or mathematical results are very welcome; contributions describing new approaches at an earlier stage of development are welcome as well, if the ideas are novel and clearly presented and argued for.
Specific topics of interest include (but are definitely not limited to):
— Symbol grounding: Learning of groundings for words and/or syntactic and/or semantic relationships, via experience interacting with objects and entities in a world
— Adaptive perception: Perception of objects and events in a world, in a manner that displays some adaptiveness, i.e. ability to perceive objects and events qualitatively different from those for which a system was previously trained or programmed
— Adaptive control: Learning patterns of actuator control in a manner that displays strong adaptiveness, i.e. ability to learn to carry out actions qualitatively different from those for which a system was previously trained or programmed
— Entity identification: Identification of which groups of percepts or atomic objects in a world are sensibly grouped together as a coherent “entity”
— Event identification: Identification of which groups of temporal happenings in a world are sensibly grouped together as a coherent “event”
— Spatial, temporal and spatiotemporal reasoning: Inference about objects and events in a world, in a manner that takes careful account of the spatial and temporal relationships between them
— Self-modeling: Building a model of the agent’s mental and physical self based on the agent’s observations of its own interactions in the world
— Modeling of other Agents: modeling of other agents, in terms of their likely behaviors in various contexts in the world
— Theory of mind: modeling of other agents, in terms of the knowledge and beliefs on which their actions are based
— Autonomy: the capabilities of an embodied AGI to find itself its own motivations and goals.
— Sensorimotor integration: methodologies for linking perception with action in an embodied AGI.


Chair: Dr. Ben Goertzel, Novamente LLC and Hong Kong Polytechnic University
The organizing committee comprises leading researchers with expertise in both AGI and cognitive robotics.
Itamar Arel, University of Tennessee, Knoxville TN, USA
Joscha Bach, Humboldt University, Germany
Antonio Chella, University of Palermo, Italy
David Hanson, Hanson Robotics,  Austin TX, USA
Matthew Ikle’, Adams State College, USA
Stephen Reed, TexAI, Austin TX, USA
Brandon Rohrer, Sandia Labs, New Mexico, USA
Pei Wang, Temple University, Philadelphia, USA

II ReteCog Workshop on Interaction 2013

II Workshop ReteCog on Interaction 2013

17-18th January, 2013
Zaragoza, Spain


In the aftermath of Turing’s anniversary, who famously proposed an interactive test of intelligence, the Spanish Network of Research in Cognitive Science –ReteCog- has chosen “INTERACTION” as the topic of its second meeting. The thematic network ReteCog is inspired by the “European Network for the Advancement of Artificial Cognitive Systems” (EuCognition). With the support of the Ministry of Science and Innovation of the Spanish Government, ReteCog aims to consolidate an interdisciplinary research network, composed by teams from 11 universities and the Spanish Science Research Council, in order to improve the understanding of cognitive systems, within the framework of the Spanish Research system.
The “II Workshop ReteCog on Interaction-2013” will be articulated through two main symposia, one on “The dynamics of agent-environment interaction” that will cover experimental and theoretical contributions to the understanding of agent-environment interactions from a dynamicist perspective, and one on “Social and emotional interaction” where the question of how to relate the role of emotions and interactive processes in the understating of other people´s minds will also be raised. Participants will have the opportunity to take part in workshops, keynote speeches and networking events involving academic experts and prestigious international researchers. It will hopefully give assistants the chance to learn about hot topics, outstanding perspectives and current results in the area of “Cognitive interaction”.

Submission of contributions

The “II Workshop ReteCog on Interaction-2013” invites contributions in issues related to the themes of both symposia (ecological psychology, perception-action coupling, sensorimotor contingencies and cognition, situated models of agent-environment interaction, philosophy of dynamical, situated and enactive approaches to cognitive science, self-organization and behavioural neuroscience, etc.). Researchers from these areas are all expected contributors or participants.


The workshop and plenary conferences will be held at the Paraninfo Building of the University of Zaragoza from the 17th to the 18th of January 2013. Zaragoza is a lively and historical Spanish city, capital of the Aragón Region. It is located in the centre of Northeast Spain and is very well communicated with other major cities, lying in the centre of the Madrid-Barcelona and Valencia-Bilbao.

Important Dates

* Submission deadline: December, 3rd, 2012.
* Notification of acceptance: December, 17th, 2012.
* Conference: 17–18th January, 2013.


Dr. Manuel G. Bedia
Dpt. Computer Science, University of Zaragoza (Spain)
Email: mgbedia unizar es