SlideShare uses cookies to improve functionality and performance, and to provide you with relevant advertising. If you continue browsing the site, you agree to the use of cookies on this website. See our User Agreement and Privacy Policy.
SlideShare uses cookies to improve functionality and performance, and to provide you with relevant advertising. If you continue browsing the site, you agree to the use of cookies on this website. See our Privacy Policy and User Agreement for details.
Successfully reported this slideshow.
Activate your 14 day free trial to unlock unlimited reading.
48.
Game World
(Environment/Level)
Five
senses
Body
Language
Knowledge
Representation
Knowledge
Making
Decision
Making
Body
Motion
Making
Information Flow
Memory
Internal Cyclic Information Flow
Sensor
Effector
Intelligence
Agent Architecture
58.
古典: 中央集権型(Central domain)
すべての知的プロセスが
順番に実行
サブサンプション : 並列 & 多層化
すべての知的プロセスが、
並列に実行
Rodney Brooks, A robust layered control system for a mobile robot
Robotics and Automation, IEEE Journal of (Volume:2 , Issue: 1 ) 1986
60.
サブサンプション・アーキテクチャ
INPUT OUTPUT
Time
Reactive
R
ロボットは障害物をみつけと
ターン。
61.
サブサンプション・アーキテクチャ
INPUT OUTPUT
Time
Reactive
R
ロボットは崖を見つけると
後退する.
62.
サブサンプション・アーキテクチャ
INPUT OUTPUT
Time
Reactive
More Abstract thinking
Abstract thinking
R ロボットは足音を聴くと、
とりあえずストップする。
63.
Subsumption Architecture
INPUT OUTPUT
Reactive
More
Abstract thinking
Theoretical thinking
Abstract thinking
R
全部掃除が終わると、
エネルギーステーションに戻る
64.
Subsumption Architecture
INPUT OUTPUT
Time
Reactive
More
Abstract thinking
Theoretical thinking
Abstract thinking
サブサンプションを
エージェント・アーキテクチャに適用。
情報を抽象化 アクションを生成
65.
Game World
(Environment/Level)
Five
senses
Body
Language
Knowledge
Representation
Knowledge
Making
Decision
Making
Body
Motion
Making
Information Flow
Memory
Internal Cyclic Information Flow
Sensor
Effector
Intelligence
Agent Architecture
66.
Game World
(Environment/Level)
Five
senses
Body
Language
Knowledge
Representation
Knowledge
Making
Decision
Making
Body
Motion
Making
Memory
Sensor
Effector
Agent Architecture
Hierarchical
Recognition
Synthesis of
motions
Knowledge
Making
Decision
Making
Motion
Making
Knowledge
Making
Decision
Making
Motion
Making
67.
Game World
(Environment/Level)
Five
senses
Body
Language
Knowledge
Representation
Knowledge
Making
Decision
Making
Body
Motion
Making
Memory
Sensor
Effector
Agent Architecture
Hierarchical
Recognition
Synthesis of
motions
Knowledge
Making
Decision
Making
Motion
Making
Knowledge
Making
Decision
Making
Motion
Making
68.
Game World
(Environment/Level)
Five
senses
Body
Language
Knowledge
Representation
Knowledge
Making
Decision
Making
Body
Motion
Making
Memory
Sensor
Effector
Agent Architecture
Hierarchical
Recognition
Synthesis of
motions
Knowledge
Making
Decision
Making
Motion
Making
Knowledge
Making
Decision
Making
Motion
Making
分散多層知能=
サブサンプション
71.
Physical
Informat
ion
Abstract
Informat
ion
More
Abstract
Informat
ion
Abstraction
Time
Decision-Making
Decision-Making
Decision-Making
Multi-Layered
Blackboard
Abstraction
Abstraction
Reduction
Reduction
Reduction
World
Sensor Effector
World Dynamics
Artificial Intelligence
Decision-MakingDecision-Making
72.
Physical
Informat
ion
Abstract
Informat
ion
More
Abstract
Informat
ion
Abstraction
Time
Decision-Making
Decision-Making
Decision-Making
Multi-Layered
Blackboard
Abstraction
Abstraction
Reduction
Reduction
Reduction
World
World Dynamics
Artificial Intelligence
Object
Object image on the
lowest layer (Umwelt)
Object image on
the second layer
Object image
on the third
layer
Decision-Making
Object image
on the top
layer
73.
Physical
Informat
ion
Abstract
Informat
ion
More
Abstract
Informat
ion
Abstraction
Time
Decision-Making
Decision-Making
Decision-Making
Multi-Layered
Blackboard
Abstraction
Abstraction
Reduction
Reduction
Reduction
World
World Dynamics
Artificial Intelligence
Object
Object image on the
lowest layer (Umwelt)
Object image on
the second layer
Object image
on the third
layer
Decision-Making
Object image
on the top
layer
74.
Physical
Informat
ion
Abstract
Informat
ion
More
Abstract
Informat
ion
Abstraction
Time
Decision-Making
Decision-Making
Decision-Making
Multi-Layered
Blackboard
Abstraction
Abstraction
Reduction
Reduction
Reduction
World
World Dynamics
Artificial Intelligence
Object
Object image on the
lowest layer (Umwelt)
Object image on
the second layer
Object image
on the third
layer
Decision-Making
Object image
on the top
layer
76.
S
(Body)
O
(Object)
Action: f
O’
Sense: p
S’
Action: f’
Sense: p’
Image of object
Image of body (=self)
R RRepresentation
77.
S
(Body)
O
(Object)
Action: f
O’
Sense: p
S’
Action: f’
Sense: p’
O’’S’’
Action: f’’
Sense: p’’
Image of object
Image of body (=self)
R R
R R
78.
S
(Body)
O
(Object)
Action: f
O’
Sense: p
S’
Action: f’
Sense: p’
O’’S’’
Action: f’’
Sense: p’’
O’’’S’’’
Action: f’’
Sense: p’’
R R
R R
R R
79.
S
(Body)
O
(Object)
Action: f
O’
Sense: p
S’
Action: f’
Sense: p’
O’’S’’
Action: f’’
Sense: p’’
R
R
R
R
Sequence of
Self
Sequence of
Object
80.
S
(Body)
O
(Object)
Action: f
O’
Sense: p
S’
Action: f’
Sense: p’
O’’S’’
Action: f’’
Sense: p’’
R
R
R
R
Sequence of
Self
Sequence of
Object
“Self” is a sequence of self. “Object” is a sequence of objects.
81.
S
(Body)
O
(Object)
Action: f
O’
Sense: p
S’
Action: f’
Sense: p’
O’’S’’
Action: f’’
Sense: p’’
R
R
R
R
Sequence of
Self
“Self” is a sequence of self. “Object” is a sequence of objects.
Vector to move
Vector to ent
Dude, Where's My Warthog: From Pathfinding to General Spatial Competence,
D. Isla, Invited talk, Artificial Intelligence and Interactive Digital Entertainment (AIIDE) 2005
http://naimadgames.com/publications.html
82.
S
(Body)
O
(Object)
Action: f
O’
Sense: p
S’
Action: f’
Sense: p’
O’’S’’
Action: f’’
Sense: p’’
R
R
R
R
“Self” is a sequence of self. “Object” is a sequence of objects.
Killzone 2 Multiplayer Bots
Remco Straatman, Tim Verweij, Alex Champandard | Paris Game/AI Conference 2009, Paris, June 2009
http://www.guerrilla-games.com/publications.html
83.
S
(Body)
O
(Object)
Action: f
O’
Sense: p
S’
Action: f’
Sense: p’
O’’S’’
Action: f’’
Sense: p’’
R
R
R
R
“Self” is a sequence of selves. “Object” is a sequence of objects.
Handling Complexity in the Halo 2 AI, D. Isla, GDC 2005
Dude, Where's My Warthog: From Pathfinding to General Spatial Competence,
D. Isla, Invited talk, Artificial Intelligence and Interactive Digital Entertainment (AIIDE) 2005
http://naimadgames.com/publications.html
132.
Abstraction
Time
World
Sensor Effector
World Dynamics
Artificial Intelligence
Object
133.
Abstraction
Time
World
Sensor Effector
World Dynamics
Artificial Intelligence
Object
Object
Object
Object
Object
明確に内的対象を
外的事物と同じように
存在するものとして
導入することができる。
134.
Decision-Making
Physical
Informat
ion
Abstract
Informat
ion
More
Abstract
Informat
ion
Abstraction
Time
Decision-Making
Decision-Making
Decision-Making
Multi-Layered
Blackboard
Abstraction
Abstraction
Reduction
Reduction
Reduction
World
World Dynamics
Artificial Intelligence
Object
Object image on the
lowest layer (Umwelt)
Object image on
the second layer
Object image
on the third
layer
Object image
on the top
layer
インフォメーション・フローは
志向性の流れを作り出してい