Differences

This shows you the differences between two versions of the page.

--- lirec_notes [2009-01-06 14:47] – created davegriffiths
+++ lirec_notes [2009-01-13 12:24] – davegriffiths
@@ Line 1: / Line 1: @@
-LIving with Robots and InteractivE Companions
+====== LIving with Robots and InteractivE Companions ======
-===Scenarios===
+<blockquote>LIREC aims to establish a multi-faceted theory of artificial long-term companions (including memory, emotions, cognition, communication, learning, etc.), embody this theory in robust and innovative technology and experimentally verify both the theory and technology in real social environments. Whether as robots, social toys or graphical and mobile synthetic characters, interactive and sociable technology is advancing rapidly. However, the social, psychological and cognitive foundations and consequences of such technological artefacts entering our daily lives - at work, or in the home - are less well understood.</blockquote>
-=Heriot Watt=
+http://www.lirec.org
-Spirit of the building:
-. Team buddy, mobile robot, collective memory for a lab team
-. Personal guide - for navigating around a university campus, remember appointments etc
-. In the wild - a gossip/chat robot - appears on a large screen in social area
-=INESC-ID=
+=====Theory=====
-. Game companion for young children
-. Personal trainer (migrate to mobile robot for jogging exercises etc)
-. Welcome to the jungle - talk to game characters through a robot, robot can alternate
-    between real and game world
-=University of Hertfordshire=
+[[Models of Social Intelligence]]
-. Fetch and carry, help with physical impairment or convenience
-. Cognitive prosthetic - memory aid for tasks etc
-. Telepresence card player - robot mediates play
-. Teaching Proxemic preferences - robot learns where to be relative to the user in different situations
-. Travelling companion - agent migration, to stay with user during home, work, shopping.
-===Architecture===
+======Architecture======
-Has to:
+See [[Lirec Architecture]] for an overview of the planned technical structure of the project.
-. Run on very different platforms
-. Reuse code across these platforms
-. Support migration at runtime between platforms
-Platforms can consist of 4 main types, mobile robot, fixed robot, handheld device or fixed graphical system. Each has it's inherent restrictions.
+=====Agent platforms=====
-=Existing robot architectures=
+The platforms currently under consideration for long term companions are:
-In the whole, there is a lack of sharing of this kind of technology. This is partly because generalising is hard in this field, considering all types of robots possible. However, Lirec has to generalise as it's using a wide variety of architectures.
+  * Mobile robots
+  * Fixed robots
+  * Handheld devices
+  * Fixed graphical systems
+=====Migration=====
+An interesting feature of the research is migration between these platforms. Agents which need to build up a long term relationship with their users will have to switch forms depending on the needs of the user at different times. The migration of an agent between devices, and how people relate to it, is a core element of the research.
+======Scenarios======
+In order to test and showcase the technology developed for Lirec, several scenarios have been designed to promote companionship. These scenarios are shared between three of the research partners.
+====Heriot Watt====
+Spirit of the building:
+  - Team buddy, a mobile robot/collective memory for a team working in a lab
+  - Personal guide - for navigating around a university campus, remembering appointments, telling you where to go
+  - In the wild - a gossip/chat robot - appears on a large screen in a social area
-NASREM/NIST RCS - NASA + ESA use a generic system with their subcontractors.
+====INESC-ID====
+  - Game companion for young children
+  - Personal trainer - which can migrate to mobile robot for jogging exercises
+  - Welcome to the jungle - talk to game characters through a robot which can alternate between real and game world
-=Methodology=
+====The University of Hertfordshire====
-In the past there have been 2 broad approaches to robot design:
+  - Fetch and carry, to help with physical impairment or provide convenience
-* Heirarchical, model based planning = expensive to maintain accurate world state model
+  - Cognitive prosthetic - memory aid for tasks
-* Behavioural approach = less state, local decisions, liable to local minima, opaque to program
+  - Telepresence card player - a robot mediates play between two people
-This can be summed up as predictive vs reactive.
+  - Teaching proxemic preferences - a robot learns where to be relative to the user in different situations
+  - Travelling companion - agent migration, to stay with user during home, work, shopping
-Current thinking is to use a hybrid approach, example BIRON. Where the predictive constrains the reactive to combine local decisions with a world model.
+======Experimental testing======
-The architecture will consist of 3 layers of abstraction:
+All scenarios developed are to be experimentally tested and showcased to the public.
-Level 1 - device layer, architecture dependant
-Level 2 - architecture dependant -> logical mappings
-Level 3 - ION, device independant
-Level 2 will provide a reference architecture with modular capabilities called competencies. Not all competencies will make sense for all architectures, and different implementations of the same competency may exist.
+TODO
-Example competencies:
+======Links======
-* Face finding
-* Expression recognition
-* Text to speech
-* Obstacle avoidance
+[[Lirec Work Packages]]
+[[http://eris.liralab.it/yarp/|YARP]] is a good example of sharing code in this way on a Linux platform.
-YARP