VVV09 Cognitive Architecture Components

From Wiki for iCub and Friends
Revision as of 17:41, 7 August 2009 by Dvernon (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

One of the main goals of the RobotCub project is to implement a cognitive architecture that will allow the iCub to exhibit neuroscientifically- and psychologically-plausible cognitive behaviour. The design of this architecture has gone through many iterations over the past few years. The current (and hopefully final) version is summarized on the iCub Cognitive Architecture wiki page.

We have some initial attempts at partial implementations of this architecture but they lack overall coherence. One of the objectives of VVV 09 is to rationalize these attempts and write a complete YARP specification of the cognitive architecture, using Lorenzo's XML description language. We will probably implemented this as a series of XML descriptions, one for each sub-system in the architecture. The task, then, is to map what exists in the iCub repository onto this specification, re-working existing modules where necessary, and also to identify the new modules that need to be written. This is where VVV 09 participants come in!

There are two components in the architecture that have not been addressed so far in the RobotCub project:

We would like VVV 09 participants to build both of these components by implementing a number of new YARP modules.