Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Imita&on	
  of	
  	
  
Human	
  Behavior	
  	
  
in	
  3D-­‐Shooter	
  Game	
  
	
  
Makarov	
  Ilya	
  
Tokmakov	
  Mikha...
Фон	
  
•  Brief	
  Review	
  of	
  Exis<ng	
  
	
  	
  	
  	
  3D-­‐shooters	
  	
  
•  Geometry	
  
•  Visual	
  Recogni...
Brief	
  Review	
  of	
  Exis<ng	
  3D-­‐shooters	
  	
  
AIST'2015,	
  Yekaterinburg	
   3	
  
Wolfenstein	
   Call	
  of...
Idea	
  
AIST'2015,	
  Yekaterinburg	
   4	
  
The	
  main	
  goal	
  of	
  our	
  
project	
  is	
  to	
  replace	
  
com...
Geometry	
  	
  
•  Types	
  of	
  the	
  objects:	
  	
  
–  walls,	
  boxes	
  
–  	
  columns,	
  doorways	
  
•  Proce...
Example	
  
AIST'2015,	
  Yekaterinburg	
   6	
  
The	
  density	
  func<ons	
  represent	
  the	
  process	
  of	
  visua...
Visual	
  Recogni<on	
  	
  Screenshot with filled holes
AIST'2015,	
  Yekaterinburg	
   7	
  
Filtering of the screenshot...
Decision	
  Making	
  Model	
  
1)  Walking	
  
a)  Bypassing	
  and	
  Search	
  
b)  Moving	
  toward	
  some	
  point	
...
Process	
  of	
  Gaming	
  	
  
•  The	
  rela<ve	
  error	
  depends	
  on:	
  
–  the	
  angle	
  between	
  BOT’s	
  ro...
Conclusion	
  
In	
  the	
  current	
  state	
  we	
  evaluate	
  the	
  parameters	
  to	
  
iden<fy	
  the	
  dangerous	...
Thank	
  you	
  for	
  aien<on!	
  
	
  
Department	
  of	
  Data	
  Analysis	
  and	
  Ar<ficial	
  Intelligence	
  
Na<on...
Upcoming SlideShare
Loading in …5
×

Makarov Ilya, Tokmakov Mikhail, Tokmakova Lada - Imitation of Human Behavior in 3D-Shooter Game

697 views

Published on

Makarov Ilya, Tokmakov Mikhail, Tokmakova Lada (HSE)
Imitation of Human Behavior in 3D-Shooter Game
AIST Conference 2015 http://aistconf.org

  • Be the first to comment

  • Be the first to like this

Makarov Ilya, Tokmakov Mikhail, Tokmakova Lada - Imitation of Human Behavior in 3D-Shooter Game

  1. 1. Imita&on  of     Human  Behavior     in  3D-­‐Shooter  Game     Makarov  Ilya   Tokmakov  Mikhail   Tokmakova  Lada     Can't  Kill  Progress  
  2. 2. Фон   •  Brief  Review  of  Exis<ng          3D-­‐shooters     •  Geometry   •  Visual  Recogni<on   •  Decision  Making  Model   •  Process  of  Gaming   •  Conclusion   AIST'2015,  Yekaterinburg   2   Фон  
  3. 3. Brief  Review  of  Exis<ng  3D-­‐shooters     AIST'2015,  Yekaterinburg   3   Wolfenstein   Call  of  duty:  Ghosts  
  4. 4. Idea   AIST'2015,  Yekaterinburg   4   The  main  goal  of  our   project  is  to  replace   commonly  used   automa<c  target   recogni<on  and   target  aiming  by  using   visual  recogni<on   methods  and  to  test   obtained  model   We  create  an   automa<c  decision   making  module  to   search  for  enemies   in  a  3-­‐D  maze  
  5. 5. Geometry     •  Types  of  the  objects:     –  walls,  boxes   –   columns,  doorways   •  Processing  the  queue:   –  finding  element  with   maximal  priority   –  recalcula<ng            dangerous  zones   –  comparing  the  first  K            queue  elements   AIST'2015,  Yekaterinburg   5  
  6. 6. Example   AIST'2015,  Yekaterinburg   6   The  density  func<ons  represent  the  process  of  visual   recogni<on  of  objects  when  we  search  for  an  enemy  but   have  to  spend  some  <me  on  processing  object’s  shapes.  
  7. 7. Visual  Recogni<on    Screenshot with filled holes AIST'2015,  Yekaterinburg   7   Filtering of the screenshot Yflgbcmyflj  pfrhsnm   Yflgbcmyflj  pfrhsnm   Yflgbcmyflj  pfrhsnm   Yflgbcmyflj  pfrhsnm  
  8. 8. Decision  Making  Model   1)  Walking   a)  Bypassing  and  Search   b)  Moving  toward  some  point  in  the  maze   c)  Finding  cover   2)  Shoo<ng   a)  Sigh<ng   b)  Opening  fire   c)  Correc<on  rela<ve  to  recoil                        and  motor  reflexes     3)  Visual  recogni<on   a)  Recogni<on  of  objects   b)  Recogni<on  of  dangerous  zones   c)  Recogni<on  of  enemy     (shoo<ng  aeer  enemy  recogni<on)     AIST'2015,  Yekaterinburg   8  
  9. 9. Process  of  Gaming     •  The  rela<ve  error  depends  on:   –  the  angle  between  BOT’s  rota<on  movements  and   direc<on  on  the  target   –  X-­‐speed   –  Y-­‐speed     AIST'2015,  Yekaterinburg   9  
  10. 10. Conclusion   In  the  current  state  we  evaluate  the  parameters  to   iden<fy  the  dangerous  zones  and  to  sight  on  enemy.   We  proceed  with  the  comparison  of  the  methods  of   visual  recogni<on  to  improve  our  model.     AIST'2015,  Yekaterinburg   10  
  11. 11. Thank  you  for  aien<on!     Department  of  Data  Analysis  and  Ar<ficial  Intelligence   Na<onal  Research  University  Higher  School  of  Economics     Makarov  Ilya:  iamakarov@hse.ru      Tokmakov  Mikhail:  matokmakov@gmail.com        Tokmakova  Lada:  lrtokmakova@yandex.ru       ©  hip://www.square-­‐enix.com       AIST'2015,  Yekaterinburg   11  

×