Browse Project Items
Viewed by Project
Projects sorted alphabetically by name. With time this collection of software
will be a repository of modules (think LEGO bricks) for multi-functional,
broad AI systems — software will be flagged by its authors according
to how modularized and pluggable it is (this feature is under development).
Current projects fall under one or more of our categories: Action Management,
Cogitation, Consumables, Generation & Planning, Interactive Systems, Multimodal
Perception, Unimodal Perception, and Motion Control [more].
Building intelligent systems that can collaborate and interact socially with people requires integrating numerous technologies in complex ways. For the A.I. researcher such integration can involve anything from connecting multiple computers and programming in multiple languages, to integrating several diverse theoretical models of perception, communication, planning and action. With a rising inter [more...] |
Owner |
Members |
Started |
Num. Items |
thorisson |
Hannes Vilhjalmsson, Stacy Marsella |
2004-12-16 |
0 |
Ambient Earth, affectionally called Amber, will try to create an image of the buzz of the Internet; what are people talking about, how are stories connected. |
Owner |
Members |
Started |
Num. Items |
christian |
|
2007-05-24 |
1 |
With regards to the fast growing IT industry and its technologies, I am completing a Mini Dissertation on the possible risks and implications of AI. With regards to genral vehicle robots, to the straight forwardness of Mobile Software Agents. Your input would be gratly appreciated. Also looking for some incidents on negative occurences. |
Owner |
Members |
Started |
Num. Items |
JonoCalder |
|
2007-02-27 |
0 |
This project is part of an international effort to unify a multimodal behavior generation framework for Embodied Conversational Agents (ECAs). We propose a three stage model we call SAIBA where the stages represent intent planning, behavior planning and behavior realization. A Function Markup Language (FML), describing intent without referring to physical behavior, mediates between the first two s [more...] |
Owner |
Members |
Started |
Num. Items |
stefankopp |
Brigitte Krenn, Stacy Marsella, Andrew N. Marshall, Catherine Pelachaud, Hannes Pirker, Kristinn R. Thórisson, Hannes Vilhjálmsson, Norman Badler, Lewis Johnson |
2006-06-14 |
1 |
CADIAHexapod is a 3D simulation of a hexapod.
Created at and for The Center for Analysis and Design of Intelligent Agents, Reykjavik University's artificial intelligence lab.
The simulation itself acts as a module, allowing each individual leg of the hexapod to be controlled by an external module, through OpenAIR and Psyclone, making it easy to try out different kinds of six-legged g [more...] |
Owner |
Members |
Started |
Num. Items |
h.thorisson |
|
2006-03-09 |
1 |
MidiShare wrapper for Psyclone |
Owner |
Members |
Started |
Num. Items |
eric@cadia |
|
2007-03-15 |
1 |
The PitchTracker analyses the pitch of a continuous speech, and describes the status of:
instantaneous pitch and derivative,
pitch slope,
speech on /on,
speech paused,
humming,
speech without a pitch,
average uninterrupted speech segment duration |
Owner |
Members |
Started |
Num. Items |
eric@cadia |
|
2007-08-08 |
1 |
We propose an XML-based Computer Vision Markup Language for use in Cognitive Vision, to enable separate research groups to collaborate with each other as well as making their research results more available to other areas of science and industry, without having to reveal any proprietary ideas, algorithms or even software. The Computer Vision Markup Language can communicate any type and amount of i [more...] |
Owner |
Members |
Started |
Num. Items |
thorlist |
Robert Fisher |
2004-11-18 |
1 |
Constructionist Design Methodology (CDM) provides a set of high-level principles for guiding development of complex A.I. systems made of heterogeneous components.
More specifically, CDM helps with:
- Construction of large, integrated systems, with a special focus on practical
systems, integrating broad functionalities including:
|
Owner |
Members |
Started |
Num. Items |
thorisson |
and numerous others. CDM has been shaped through use in a number of real projects |
2005-12-29 |
0 |
A C# port of the JavaOpenAir code.
Includes CSPoster, CSReader, CSTrackFixer and CSMovement.
Done as a part of Thor List's Computer Vision course at Reykjavik University. |
Owner |
Members |
Started |
Num. Items |
snorrk |
Freyr Magnusson |
2005-12-21 |
1 |
Course E6998-004, Dept. of Computer Science, Columbia University, Fall 2002.
Professor K. R. Thórisson, Ph.D.
Interdisciplinary course focusing on the integration and architectural challenge of designing intelligent, embodied agents that can interact and communicate with real humans in real situations. Weaves together aspects from cognitive science, psychology and arti [more...] |
Owner |
Members |
Started |
Num. Items |
thorisson |
|
2004-08-24 |
0 |
Files for setting up Icelandic voice for Festival. Includes sound files and basic language files.
To use this Festival 1.95 or later must be set up. The files should then be extracted from the tarball into the festival directory. Festival should then find the voice automatically when loaded.
NB. The Festival shell does not accept other then ASCII 128 symbols. Icelandic only letters can thus [more...] |
Owner |
Members |
Started |
Num. Items |
steinst |
|
2005-11-25 |
1 |
Jython port for OpenAIR, using JavaOpenAIR for messaging. |
Owner |
Members |
Started |
Num. Items |
brynjar |
|
2007-08-25 |
1 |
A knowledge base spanning common sense. Over 10,000 axioms, where each axiom is made of triples. The knowledge was based on a subset of the Open Mind corpus. The knowledge base is divided into three hundred contexts. Inference is carried out by spreading activation to other axioms with the same triple(s) and a simple threshold based on the number of triples in an axiom.
|
Owner |
Members |
Started |
Num. Items |
kennedycolm |
David Whitten. |
2004-09-09 |
0 |
mBrane: Versatile Communication for Intelligent Distributed Systems
mBrane
Wiki
Forum
|
mBrane is a new registration-based message routing framework with a rich feature set and blazing speed. In mBrane components can register for and post data, either as discrete messages or as continuous data steams, through the same simple interface and protocol. mBrane is designed to be an extremely fast and easy-to-use communication system where routing is directly done by the local networ [more...] |
Owner |
Members |
Started |
Num. Items |
mbrane |
Eric Nivel, Kris Thorisson, Gudny Jonsdottir |
2008-02-18 |
0 |
MediaHub is intelligent multimedia distributed platform hub for decision-making (fusion and synchronisation) over multimodal data. MediaHub aims to integrate and synchronise language and vision data in such a way that the two modalities are complementary to each other. Key to the development of MediaHub is the use of the OpenAIR routing and communication protocol that allows the development of the [more...] |
Owner |
Members |
Started |
Num. Items |
Glenn Campbell |
Tom Lunney, Paul McKevitt |
2006-10-25 |
0 |
We are working on a proposal for an upper- and mid-level ontology for cognitive systems. The goal of the effort is to help standardize the message types used for input and output of cognitive modules, so that modules can be "plugged into" an architecture with minimal modifications to their input and output. The effort will produce specifications that can be used by any developer of cognitive modul [more...] |
Owner |
Members |
Started |
Num. Items |
thorisson |
Gudny R. Jonsdottir, Vignir Hafsteinsson, Arsaell Johannsson |
2006-05-25 |
0 |
MIRAGE is an embodied, graphical agent that can communicate with users about real and virtual objects in the user's environment. A user enters the augmented reality room and puts on the "magic glasses". Through the glasses the user can still see the room, but superimposed is now the floating graphical image of MIRAGE.
The room that MIRAGE lives in is fitted with trackers that make Mir [more...] |
Owner |
Members |
Started |
Num. Items |
thorisson |
H.Benko, D.Abramov, A.O.Arnold, S.Maskey, A.Vaseekaran |
2004-04-26 |
1 |
I have written a book called 'Principia Intellegentia: The principles governing human and machine intelligence'. This book makes the case for considering the phenomenon of intelligence in humans to be entirely bound up with their individual ability to learn. It does this by setting out a high-level description of how humans learn - called 'IDEAL' - and then showing how this description accounts [more...] |
Owner |
Members |
Started |
Num. Items |
rdkingdon |
|
2007-10-03 |
0 |
Psyclone is a platform for building hybrid modular, distributed systems. The free downloadable version runs at present on three operating systems, Windows, Mac OS X and Linux.
Psyclone bridges platforms and programming languages, helping with the design and implementation of systems with many components that interact in complex ways. Psyclone is currently being used in European and U.S [more...] |
Owner |
Members |
Started |
Num. Items |
cmlabs |
|
2007-10-22 |
0 |
An editor for psySpecs, the central XML files that can hold a full architecture specification of a Psyclone system.
The task of constructing a large scale AI system raises a number of challenges, such as designing and managing a large amount of modules and the flow of communication between them. Psyclone uses the OpenAIR protocol proposed and maintained by Mindmakers to assist the proc [more...] |
Owner |
Members |
Started |
Num. Items |
psySpecEditor |
Ágúst Karlsson, Chris Pennock |
2007-04-30 |
0 |
Our Wiki at ISI hosts new follow-up material to the workshop.
The overall goal of this workshop was to further the state of research on multimodal generation by enabling (and getting) people in the field to work together.
To this end, we are working towards:
- Framing the problem of mult [more...] |
Owner |
Members |
Started |
Num. Items |
thorisson |
Catherine Pelachaud, Hannes Vilhjalmsson, Stefan Kopp |
2005-07-29 |
0 |
The generation of natural multimodal output for embodied conversational agents requires a time-critical production process with high flexibility. To scaffold this production process and encourage sharing and collaboration, a working group of ECA researchers has introduced the SAIBA framework (Situation, Agent, Intention, Behavior, Animation). The framework specifies multimodal generation at a ma [more...] |
Owner |
Members |
Started |
Num. Items |
hannes |
Norman Badler, Lewis Johnson, Stefan Kopp, Brigitte Krenn, Stacy Marsella, Andrew N. Marshall, Catherine Pelachaud, Hannes Pirker, Kristinn R. Thorisson |
2006-08-25 |
0 |
The Task Matrix is a repository for storing and describing tasks in a robot-independent manner. Specific interfaces are defined for interacting with the skills layers of robots and the perceptual modules of the robot. This work is currently done at my job at the Honda Research Institute for the humanoid robot Asimo. |
Owner |
Members |
Started |
Num. Items |
victorng |
Evan Drumwright |
2007-01-27 |
0 |
ToonFace is an evolving specification of an animation system for algorithmic/parametric generation of facial movement and speech. ToonFace provides a useful representation of muscles and motion control in systems that generate movement in real-time and where such movement can be interrupted at human perception-action loop levels (around 100 msec).
While everyone seems to be striving for the most [more...] |
Owner |
Members |
Started |
Num. Items |
thorisson |
Catherine Pelachaud, Zsofia Ruttkay, Kristleifur Dadason |
2005-11-16 |
1 |
Is it possible to build physical models of computer models? Sure, it just takes an aweful lot of LEGO blocks.
When I was at LEGO my team and I developed an artificially intelligent character called Puff the Magic LEGO Dragon. I spent a lot of time explaining the workings of the Ymir architecture that powered Puff's [more...] |
Owner |
Members |
Started |
Num. Items |
thorisson |
|
2004-11-20 |
0 |