Slide 1

designpadΤεχνίτη Νοημοσύνη και Ρομποτική

1 Δεκ 2013 (πριν από 3 χρόνια και 8 μήνες)

61 εμφανίσεις

AGI
-
09

Scott
Lathrop

John Laird

1

2


Cognitive Architectures


Amodal
, symbolic representations & computations


No
general reasoning

with perceptual
-
based representations (
Barsalou

1999, 2008)






Resulting in…



Ad
-
hoc reasoning in tasks rich with spatial and visual properties


“Bolted
-
on” task
-
dependent components








What we desire…


“Best of both worlds”
multi
-
representational
,
task
-
independent

approach


Functionality


Computational advantage


Link
perceptual
-
based thought
and
cognition






3

Representation

Processing

Uses

Example

Symbolic


Amodal


Symbolic
manipulation


General
Reasoning/Control


Qualitative Spatial &
Visual Reasoning



feature (
letter
-
B
, line)

color(
letter
-
B
, blue)


feature(
box
, corner)

color(
box
, yellow)


on(
letter
-
B
,
box
)

Quantitative spatial


Amodal
/Perceptual
-
based


(Spatial Imagery)

Mathematical
manipulation


Dynamical Systems
(motion models)

Spatial Reasoning

(Generic Shapes)


Facilitate building visual
depictive representation


letter
-
B


location <2,3,
-
2> orient 0


length 2 height 4

box


location <0,0,0> orient 20


length 6 height 4 width 2

Visual depictive


Modality
-
specific/Perceptual
-
based


(Visual Imagery)

Mathematical
manipulation


Depictive
manipulation

Spatial Reasoning

(Specific Shapes)


Visual Feature
Recognition


4

Enemy

Scout
-
2

Enemy

Scout
-
1

Scout
-
1

(Agent)

Scout
-
2

(Teammate)

Enemy

Scout
-
3


Actual Situation

Scout
-
2

(Teammate)

Enemy Scout
-
1

Teammate’s View

Observed

Enemy

Scout
-
2

Scout
-
1

(Agent)

Agent’s View

Observed

Enemy

Scout
-
2

Hypothesized

Enemy

Scout

Hypothesized

Enemy

Scout

“Key”

Terrain

Imagined Situation

5

6

SVI



Quantitative spatial



Scene
-
graph


Viewpoint

Object Map STM

Refresher

Stimulus
-
Based

Refresh

“Rendered”

Image

Visual
-
Spatial STM

Object

Set

Obj
A
,Obj
B,…

Feature

Set

Spatial


Set

Feature

Set

Object

Set

Obj
A1
,Obj
A2,…

Spatial


Set



Visual depictive



Set of 2D bitmaps

Visual Buffer STM



Shape


Texture



Spatial configuration

Perceptual
LTM

“What” Inspectors

“Where” Inspectors

Soar

Symbolic STM


Goals


Current State



Process

Productions

Memory

Symbols

Visual
Symbols

Data

Path

Control

Path

Symbolic (Procedural) LTM

IMAGERY OPERATORS

Construct

Generate

Transform

Inspect

TASK OPERATORS


Constructor

Manipulator



Pixel
-
level rewrites (Furnas, 2000)



Production
-
like rules (LHS/RHS)



Shared image (i.e. working memory)



LHS and RHS are pixel patterns



Conflict resolution scheme (sequencing)



Processing may match other orientations



Active manipulation of shapes



Contrast with other image processing



Computer vision

o

Sentential manipulations

o

F
ilters (e.g. Gaussian) where each pixel is
rewritten as a specific function of its neighbors’
values



Cellular Automata

o

Finite State Machines

o

Next state of a cell based on current state and
state of its neighbors

o

Rather than rewriting many local configurations
at once

=
“don’t care”

“2x2
reduce”

“nibble

up”

“nibble left”

8



Takes specific shape of no
-
go terrain and obstacles
(yellow) into account



Attention window
shift controlled
by Soar



Pixel rewrite rules sent from Soar to SVI



Determine approximate path coverage by overlaying
each scout’s view frustum



Simulate alternate view orientations to determine
“best” path coverage

*

Steep
Terrain

All
Other

Obstacles

Mark Obstacles

*

*

*

*

Layer

0
-
1

*

Distance Field Flood

Layer

0
-
1

Layer

1
-
2

Mark Path

Start
-
Layer 2

Layer 2
-
1

Layer 1
-
0

Layer 1
-
0

9

10

-1
-0.9
-0.8
-0.7
-0.6
-0.5
-0.4
-0.3
-0.2
-0.1
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0
30
60
90
120
150
180
210
240
270
300
330
360
390
Information

Simulation Time

Soar+SVI
Soar-SVI
Observer
Tracker

General

reasoning with symbolic and perceptual
-
based
representations where the reasoning emerges from the
combination of the representations



Soar


Symbolic representations and computations


Goals and high
-
level knowledge


Controls imagery processing



Spatial and Visual Imagery (SVI)


Quantitative spatial and visual depictive representations and computations


Leverages perceptual mechanisms



Future Work
-

Push architecture closer to sensory input (Robotics)

11