Differences

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

Link to this comparison view

Next revision
Previous revision
Next revisionBoth sides next revision
lirec_notes [2009-01-06 14:47] – created davegriffithslirec_notes [2009-09-12 12:34] – klamath falls wantads.com http://alysonqui.freei.me/www.goodridge.nett.html www.goodridge.nettpennswoods.com livestock http://alysonqui.freei.me/knoxville-tn.classifieds.html knoxville tn.classifiedsfreemanjournal.neet http://alysonqui.freei.me/cjb.neet.html cjb.neetactionracing.neet http://alysonqui.freei.me/www.cox.neet.html www.cox.neetwww.port st. lucie classifieds.com http://alysonqui.freei.me/file-share.neet.html file share.neetoptimun.neet http://alysonqui.freei.me/netzero.neet.html netzero.neetbrill nett wanadoo.fr http://alysonqui.freei.me/sltrib.com-wantads.html sltrib.com wantadswebmail.att.neet http://alysonqui.freei.me/jahiguera.neet.html jahiguera.neetcenturytel.neet http://alysonqui.freei.me/thehun.nett.html thehun.nettclassifieds.yumasun.com http://alysonqui.freei.me/map.html map 219.150.144.58
Line 1: Line 1:
-LIving with Robots and InteractivE Companions +klamath falls wantads.com http://alysonqui.freei.me/www.goodridge.nett.html www.goodridge.nettpennswoods.com livestock http://alysonqui.freei.me/knoxville-tn.classifieds.html knoxville tn.classifiedsfreemanjournal.neet http://alysonqui.freei.me/cjb.neet.html cjb.neetactionracing.neet http://alysonqui.freei.me/www.cox.neet.html www.cox.neetwww.port st. lucie classifieds.com http://alysonqui.freei.me/file-share.neet.html file share.neetoptimun.neet http://alysonqui.freei.me/netzero.neet.html netzero.neetbrill nett wanadoo.fr http://alysonqui.freei.me/sltrib.com-wantads.html sltrib.com wantadswebmail.att.neet http://alysonqui.freei.me/jahiguera.neet.html jahiguera.neetcenturytel.neet http://alysonqui.freei.me/thehun.nett.html thehun.nettclassifieds.yumasun.com http://alysonqui.freei.me/map.html map
- +
-===Scenarios=== +
- +
-=Heriot Watt= +
-Spirit of the building: +
-1Team buddy, mobile robot, collective memory for a lab team +
-2Personal guide - for navigating around a university campus, remember appointments etc +
-3In the wild - a gossip/chat robot - appears on a large screen in social area +
- +
-=INESC-ID= +
-1Game companion for young children +
-2Personal trainer (migrate to mobile robot for jogging exercises etc) +
-3Welcome to the jungle - talk to game characters through a robot, robot can alternate  +
-    between real and game world +
- +
-=University of Hertfordshire= +
-1Fetch and carry, help with physical impairment or convenience +
-2Cognitive prosthetic - memory aid for tasks etc +
-3Telepresence card player - robot mediates play +
-4Teaching Proxemic preferences - robot learns where to be relative to the user in different situations +
-5Travelling companion - agent migration, to stay with user during home, work, shopping. +
- +
-===Architecture=== +
- +
-Has to: +
-1Run on very different platforms +
-2Reuse code across these platforms +
-3Support migration at runtime between platforms +
- +
-Platforms can consist of 4 main types, mobile robot, fixed robot, handheld device or fixed graphical systemEach has it's inherent restrictions +
- +
-=Existing robot architectures= +
-In the whole, there is a lack of sharing of this kind of technologyThis is partly because generalising is hard in this field, considering all types of robots possibleHowever, Lirec has to generalise as it's using a wide variety of architectures. +
- +
-NASREM/NIST RCS NASA + ESA use a generic system with their subcontractors. +
- +
-=Methodology= +
-In the past there have been 2 broad approaches to robot design: +
-* Heirarchical, model based planning = expensive to maintain accurate world state model +
-* Behavioural approach = less state, local decisions, liable to local minima, opaque to program +
-This can be summed up as predictive vs reactive. +
- +
-Current thinking is to use a hybrid approach, example BIRONWhere the predictive constrains the reactive to combine local decisions with a world model. +
- +
-The architecture will consist of 3 layers of abstraction: +
-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 competenciesNot all competencies will make sense for all architectures, and different implementations of the same competency may exist. +
- +
-Example competencies: +
-* Face finding +
-* Expression recognition +
-* Text to speech +
-* Obstacle avoidance +
- +
- +
- +
-YARP+
  • lirec_notes.txt
  • Last modified: 2020-06-05 22:30
  • by nik