Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revisionBoth sides next revision | ||
lirec_notes [2009-01-06 15:02] – davegriffiths | lirec_notes [2009-01-06 15:17] – davegriffiths | ||
---|---|---|---|
Line 3: | Line 3: | ||
LIREC aims to establish a multi-faceted theory of artificial long-term companions (including memory, emotions, cognition, communication, | LIREC aims to establish a multi-faceted theory of artificial long-term companions (including memory, emotions, cognition, communication, | ||
- | Key areas of the research will focus on are: | + | ==Agent platforms== |
- | ==Long | + | The platforms currently under consideration for long term companions |
- | Robots and agents which build up a long term relationship with their users. | + | * Mobile robots |
+ | * Fixed robots | ||
+ | * Handheld devices | ||
+ | * Fixed graphical systems | ||
- | ==Agent migration== | + | ==Migration== |
- | In order to maintain | + | |
- | * Mobile robot | + | An interesting feature of the research is migration betwen 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 |
- | * Fixed robot | + | |
- | * Handheld device | + | |
- | * Fixed graphical system | + | |
- | + | ||
- | This migration between | + | |
===Scenarios=== | ===Scenarios=== | ||
- | The scenarios are to be considered preliminary ideas for showcasing | + | In order to test and showcase |
==Heriot Watt== | ==Heriot Watt== | ||
Line 33: | Line 31: | ||
between real and game world | between real and game world | ||
- | ==University of Hertfordshire== | + | ==The University of Hertfordshire== |
- Fetch and carry, help with physical impairment or convenience | - Fetch and carry, help with physical impairment or convenience | ||
- Cognitive prosthetic - memory aid for tasks etc | - Cognitive prosthetic - memory aid for tasks etc | ||
Line 39: | Line 37: | ||
- Teaching Proxemic preferences - robot learns where to be relative to the user in different situations | - 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. | - Travelling companion - agent migration, to stay with user during home, work, shopping. | ||
+ | |||
+ | ===Experimental testing=== | ||
+ | |||
+ | All scenarios are to be experimentally tested in public. | ||
===Architecture=== | ===Architecture=== | ||
- | Has to: | + | The technology developed for lirec is shared between the research partners, and has to: |
- Run on very different platforms | - Run on very different platforms | ||
- Reuse code across these platforms | - Reuse code across these platforms | ||
Line 56: | Line 58: | ||
==Methodology== | ==Methodology== | ||
In the past there have been 2 broad approaches to robot design: | In the past there have been 2 broad approaches to robot design: | ||
- | * Heirarchical, model based planning = expensive to maintain accurate world state model | + | * Hierarchical, model based planning = expensive to maintain accurate world state model |
* Behavioural approach = less state, local decisions, liable to local minima, opaque to program | * Behavioural approach = less state, local decisions, liable to local minima, opaque to program | ||
This can be summed up as predictive vs reactive. | This can be summed up as predictive vs reactive. | ||
- | Current thinking | + | The plan is to use a hybrid approach, example BIRON. Where the predictive constrains the reactive to combine local decisions with a world model. |
The architecture will consist of 3 layers of abstraction: | The architecture will consist of 3 layers of abstraction: | ||
- | * Level 1 - device layer, | + | * Level 1 - device layer, |
- | * Level 2 - architecture | + | * Level 2 - platform |
- | * Level 3 - ION, device independant | + | * Level 3 - ION, platform independent |
- | 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 | + | Level 2 will provide a reference architecture with modular capabilities called competencies. Not all competencies will make sense for all platforms, and different implementations of the same competency |
Example competencies: | Example competencies: |