behaviour in ootw simulators
play

Behaviour in OOTW Simulators - PDF document

Behaviour in OOTW Simulators zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA AI for OOTW Representing Plausible ~~ HVR C O N S U L T I N G S E R V I C E S LIMITED 0 0 1 4 2 0 zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA 0 0 1 4 2 0


  1. Behaviour in OOTW Simulators zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA AI for OOTW Representing Plausible ~~ HVR C O N S U L T I N G S E R V I C E S LIMITED 0 0 1 4 2 0 zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA 0 0 1 4 2 0 zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA SELBORNE H O U S E . M I L L L A N E . A L T O N . H A M P S H I R E G U 3 4 2QJ 87977 8 9 8 1 9 @ w w w . H V R G r o u p . c o m

  2. , Dr Stephen Curram zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA HVR Consulting Services Ltd * steve.curramQ hvr-csl.co.uk @ zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA Dr Mark Cusack QinetiQ, Malvern e Mirek Gliniecki HVR Consulting Services Ltd sorts of situations they may be faced with : zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA -Background Purpose of overatl study is to create simulators that allow commanders who may be involved In OOTW to experience the 0 Multiple factions and agencies 0 Highly political environment 0 Restrictive ROE 0 Media coverage and public opinion 0 Multiple information sources Background (2) 2 " b 0 Purpose of slmulators is to provide a challenging component zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA and thought provoking envlronment designed to be anatysis 0 The slmulators are tools 0 They will conform to the High Level Architecture (HLA) requirements 0 Use Java and JavaBeansTM technology o f the study 0 AI is only one * Pilot Is a peace-keeping scenario 1

  3. @ zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA ldentlficatlon of behavlour types and requirements zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA for zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA of zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA 0 zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA - - - . ~ - ~ - ~ Study Approach ~~ OOTW Al slmulstors Review of technology . end case studies to generate shortlist of approaches for further InVestIgatlofI Develop stand-alone AI oblects for analysis 0 T8M AI objects In an Integrated environment Use In pllot slmulstlon model L I 3 - Alms of the AI trylng to be& the Al- zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA 0 Provide plauslble behaviour In simulation I from a player's perspective -computer generated actors -occurrence of events 0 Qive player somethlng to think about 0 Be responsive to player's actions Not to be too transparent - player should be immersed In environment rather than G Intelligence, BUT Itss ~ruficiai CI I t la more Important that behaviour- plausible to a player rather than for the commei . iter gamesthan traditional mllitary models 2

  4. take ICCOYIII zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA Of zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA 2 = * ; Approaches Considered MM zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA - doss not . Random Sampling of condltloM. though not pmdlGbble. could be mllmly to set up and have overhaad zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA comblned apprOaChM WWh O l h W Knowledgbsued system8 (& mlaM) ~ u n be MO pmdlst.ble ll simple, Whlb S M n g UP N I - a n mom COmplW falls rapldly M rub8 become elmplar but mom F q am gonerdly Loglc- NIW th.n @Se, made some experlma In cholw . powMlul of hmy nglona, Ilnguletis can hdp In m a h l m m CubBu.d Fmasonlng - twaLlng SCMUIO~ sy.1.ma can b t l m e full conaumlng ot shell, wrsbna may be useful ahnplu for Rmgnlalng when scr1pt.d went. u m occur lo zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA Machlnaa urlng zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA P E Approaches Consldered (2) M.chlMe - commonly nnlm uwd In computer S m games, elmple - adapmtlon snl up. u n go1 pndktsble (or p1ay.r o f f l n b F q 8uQ Machl- Stale funy NIM, h m l n g popululn computer gMM. memb.nhlp funcllone could be wed - for nndom aampllng B a y ~ l m Bsll.1 W o r k s mpnamtatlon of pamrful fauora on bhavlour, can b. up, dlMcully drmcult to ml Natworke (varlow h/pw) - d valldallon Neural md.ptln, p o w 0 1 I ~ l mp"tatlon but Ums consuming and dllRcult to 9.1 up and vdldam Algorkhmr - Q e d c adaptlw but too SIW (or Intemdive almulsllon " 2 Short-llsted Approaches CI Finite State Machine (FSM) - for *Impls Whavlour - gensrlc FSM obJset to which " and t u m . 1 . hnamons smsdded -MSybSdUp 3

  5. @ zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA - zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA Short-listed Approaches zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA 0 zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA Fuzzy State Machine (FuSM) for more complex behaviour - linguistic or numerical Inputs - smoother transltions between states - create generlc FuSM to which terms and fuzzy rules canbeadded - state can be selected from centre of gravity or using random samollns from fuuv resion @ Short-listed Approaches " 0 Simplified Case-Based Reasoning - prescrlpted events or event generators - conditions for launching events, lncludlng time windows - random element - generlc object that llnks to event and allows condltlons to be speclfled based on other objects present in simulation Y towards zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA Behaviour Type - Attitude 2 " I @ e Attitude of an actor towards other actors - zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA may differ at different levels, e.g. factlon leaders UN, or factlon soldier towards UN - use Finite State Machlne or Fuzzy State Machine 1 c- 1 1 1 Y I I L 4

  6. Behaviour Type zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA - Negotiation I l l l W U "I~"j,"l.-l~nMX*IXU> zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA % E ! M , . b "1" 0 Negotiation between actors process over time zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA - player has role as a mediator, and suggests - compromise solutions response o f actors depends on the weighted dlstance from thelr ideal solution and thelr attitude towards the negotiatlons - Use Fuzzy State Machine - likely to be iterative L zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA Behaviour Type - Negotiation zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA 6 % 3liEZE; - u _ _ _ 1 C I L Y / \ Behaviour Type - Event zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA I @ 0 Scripted events need to occur at plausible times - -- e.g. negative newspaper stories on refugee camp conditions only when conditions are bad I n k * tkiLb*om 5

  7. . zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA IC zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA aP zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA Current Work 6

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend