close

Вход

Забыли?

вход по аккаунту

?

The Alive Project Bruce M. Blumberg, MIT

код для вставкиСкачать
The Alive Project
Bruce M. Blumberg, MIT
Sidney D’Mello
Control of Autonomous Agents
Overview:
пЃ®
пЃ®
пЃ®
пЃ®
пЃ®
Agent: Autonomous Dog (Silas T. Dog)
Environment: 3D artificial world and people.
Sensors: Synthetic vision.
Goals:
Satisfy internal motivations.
Obey the user.
Actions:
Respond to gestures of the user.
Other basic actions (satisfy drives, etc..)
Goals:
пЃ®
пЃ®
Autonomy:
Pursues its own agenda.
Senses the environment.
Acts on the environment.
Directability:
Action selection may be independent of the behavior
system.
Suggest how the action should be performed.
Multiple Levels of Control
M o tivatio nal
L evel
T ask
L evel
D irect
L evel
high
low
yo u are
hungry
go to that
tree
turn w alk
m o to r o ff
C ontrol D iagram
• Motivational Level: Change the dog’s current motivation.
• Task Level: Supply a high level directive.
• Direct Level: Direct control of the motor system.
Behavior Model
Design goals:
пЃ® Optimal action selection model.
пЃ® Model the effect of external stimuli and internal
motivation.
пЃ® Multiple behaviors may suggest actions and execution
preferences.
пЃ® Maintain a winner takes all architecture.
пЃ® Support for motivational and task level directions at run
time.
Behavior Architecture
h igh
B eh a vior
ab straction b arriers
m otor system
C on troller
M otor Sk ills
D egree's of F reed om
G eom etr y
lo w
B eh a vior A r ch itectu r e
•Three central parts:
Behavior
Motor Skills
Geometry
•Two layers of abstraction:
Controller
Degree’s of Freedom
Geometry
пЃ®
пЃ®
пЃ®
Provides the shapes and transforms.
Issued by the motor system.
Manipulated over time for animation.
Motor System
пЃ®
пЃ®
пЃ®
Components: Controller, Motor Skills, Degree of Freedom
Commands: left, sit, forward, back,….
Importance:
Translates behaviors into commands.
Abstraction barrier (forward --- walking, swimming).
Provides a generic set of commands (eat, sleep).
Provides resource management.
Degrees of Freedom
пЃ®
пЃ®
пЃ®
“Knobs” to modify the underlying geometry.
Used to wag the tail, move a joint,…
Importance:
Provides a locking mechanism.
Provides an abstraction mechanism.
Motor Skills
пЃ®
пЃ®
пЃ®
пЃ®
пЃ®
Examples: lower head, turning, walking,….
Can be turned on or off.
Coordinates DOF’s to perform smooth motion.
Spring loaded.
Reduces bookkeeping.
Controller
пЃ®
пЃ®
пЃ®
пЃ®
Abstraction barrier between behavior system and motor
skills.
Maps commands to turn on or turn of motor skills.
Example: forward command --- walk, move motor skill.
Command Types:
Primary command
Secondary command.
Meta command.
Behavior System
пЃ®
пЃ®
Hierarchical network of
goal-directed entities.
Examples:
move-to-tree
search-for-food
knock-on-door
Behavior Diagram
T ask
Sensors
B eh avior
M otor S ystem
D irect
B eha vior D ia g ra m
U ser
M otivation al
Releasing Mechanisms
пЃ®
пЃ®
пЃ®
пЃ®
пЃ®
Filters sensory input.
Identify relevant objects and/or events.
Typically output a continuous value.
May be shared among multiple behavior.
Example:
weak stimulus/strong motivation
strong stimulus/weak motivation
Internal Variables
пЃ®
пЃ®
пЃ®
пЃ®
Used to model the internal state.
Expressed as continuous values.
Modified by behaviors.
May be shared by multiple behaviors.
Behavior Groups
•Groups of mutually inhibiting behaviors.
•Loose hierarchical structure:
Upper Level: Driven by motivation (engage-in-feeding).
Lower Level: Driven by sensory input (pounce, chew).
Inhibition and Level of Interest
пЃ®
пЃ®
пЃ®
пЃ®
пЃ®
Avalanche Effect.
Insures that only one behavior will be non-zero.
Controls the persistence of behaviors.
Manages the level of interest of behaviors.
Provides a mechanism for the winner takes all arbitration.
Issuing Commands:
пЃ®
пЃ®
пЃ®
пЃ®
Winning behavior and its children: Primary commands.
Losing behaviors: Secondary and Meta commands.
Winning behavior can overrule a secondary command.
Winning behavior can ignore a meta command.
Integration of Directability
пЃ®
пЃ®
пЃ®
пЃ®
Motivational control: Access to internal variables.
Behavior control:
Access to Releasing Mechanism.
Possible to activate behaviors.
Sensory control: imaginary sensory input.
Motor Control:
Shut of the behavior system.
Issue secondary or meta commands.
Implementation Specifics
пЃ®
пЃ®
пЃ®
пЃ®
пЃ®
пЃ®
Responds to a dozen user gestures.
40 Behaviors.
11 Behavior Groups.
40 Releasing Mechanisms.
8 Internal Variables.
70 Motor Commands.
Conclusions
пЃ®
пЃ®
пЃ®
пЃ®
Action selection algorithm suits needs.
Autonomy and directability are not mutually exclusive.
Blend of autonomy and direction provide more control.
Control architecture can be easily incorporated onto
different agents.
References:
пЃ®
пЃ®
Multi-Level Direction of Autonomous Creatures for
Real-Time Virtual Environments
Bruce M. Blumberg and Tinsley A. Galyean
Expressive Autonomous Cinematography for
Interactive Virtual Environments
Bill Tomlinson, Bruce Blumberg, Delphine Nain
Документ
Категория
Презентации
Просмотров
5
Размер файла
236 Кб
Теги
1/--страниц
Пожаловаться на содержимое документа