SPRINGERLINK SISTEMAS INTELIGENTES

8/6/2019 SPRINGERLINK SISTEMAS INTELIGENTES

http://slidepdf.com/reader/full/springerlink-sistemas-inteligentes 1/10

4INTELLIGENT

SYSTEMS





Arch i t ec tures for Co m plex Behav iour

Inspired in the Nervo us System

R o b e r t o M o r e n o - D i a z 1 a n d J o s e M i r a M i r a 2

C e n t r o I n t e r n a c i o n a l d e In v e s t i g a c io n e n C . d e l a C o m p u t a c i o n U n i v e r s i d a d d e L as

P M m as d e Gran C an a r i a , C an a ry I s lan d s, S p a in .

2 Dp t o . d e I n t e l i g e n c i a Art i f ic ia l UNED, Madr id , Spa in .

A b s t r a c t . G e n e r a l i z e d r o b o t i c s y s t e m s a r e p r o b a b l y o n e o f t h e m o r ec o m p l e t e p a rad i g m s o f n a t u ra l b eh av i o u r , s o t h a t t h e y c a n p r o p e r l y b e

c o n s i d e r t o s h o w ar t if i c ia l behav iour in the h igher sense o f the te rm . A

genera l ized robo t ic sys tem i s h e r e u n d e r s t o o d a s t h a t a r t if ic i al s y s t e m

capab le o f sens ing the env i ronm ent , perce ive i t an d in te rp re te i t in t e r m s

of mo re o r l ess genera l models o f the env i ron me nt an d o f i tself ; capab le

a l so o f com put ing ap prop r ia te s t ra teg ies o f ac t ion , by p lann ing an d b y

finding plausible act ion m etho ds. A nd ca pable, f inal ly , of f i r ing sequenc es

of moto r and ef fec to rs ac t ions, hav ing ways o f con tro l l ing sa id ac t ions .

1 I n t r o d u c t i o n

S u c h a c o m p l e t e s y s t e m i s s ti ll a d e s i d e r a t u m n o w a d a y s t h o u g h n o t s o h i g h l y

s o p h i s t i c a t e d t y p e s o f a r ti fi c ia l b e h a v i o u r c a n b e , a t l e a st t h e o r e t i c a l ly , o b t a i n e d

b y p i e c i n g t o g e t h e r d i f f e re n t c o m p o n e n t s f r o m t h e f ie ld s o f r o b o t i c s a n d a r t if i c ia l

i n t e l l i g e n c e , a n d b y u s i n g t h e i n s p i r i n g h e l p o b t a i n e d f r o m n a t u r M s y s t e m s .

O n e o f t h e c e n t r a l is s u es t o t h is g o a l is h o w s e n s i n g, p e r c e p t i o n a n d a c t i o n

a r e i n t e g r a t e d i n n o n t r i v i a l m a n n e r s . T h o u g h t h i s i s n o t a r e c e n t g o a l , m o d e r n

a r t i f ic i a l in t e l l ig e n c e t o o l s a r e s h i d i n g s o m e l i g h t t o b u i l t p r a c t i c a l d e v i c e s . M o r e

t h a n t w e n t y y e a r s ag o , m e m b e r s o f a r e se a r c h p r o g r a m c a r r ie d o n a t t h e I n s t r u -m e n t a t i o n L a b o r a t o r y o f t h e M a s s ac h u s se t s I n s t i t u t e o f T e c h n o l o g y [7], t h o u g h

i n i t i a l l y d e a l i n g w i t h a r t i f i c i a l v i s u a l p e r c e p t i o n , s o o n r e a l i z e d t h a t m a n y a r t i f i -

c i a l p e r c e p t u a l p r o b l e m s w e r e n o t c o m p r e h e n s i b l e u n l e s s t h e p e r c e p t u a l s y s t e m

w a s c o n s i d e r e d t o b e i n t e g r a t e d w i t h i n a k in g o f r o b o t i c s s y s t e m . T h u s , t h e

q u e s t i o n s o f t h e o p t i m a l u s e o f v i s u al d a t a w e r e t r e a t e d i n c o n j u n c t i o n w i t h t h e

u s e o f s a id i n f o r m a t i o n t o c o n v e rg e i n to a " m o d e o f a c t i o n " , b y s o m e t y p e o f

c o o p e r a t i v e d e c i s i o n p r o c e s s [8] [9 ]. W e d i s s e c t h e r e a f r a m e f o r s u c h i n t e g r a t i o n ,

w h i c h i s g e n e r a l e n o u g h t o b e n o n - t r i v i a l , b u t t h a t c a n b e - a n d i s b e i n g - u s e d

t o d e s ig n p r a c t i c a l r o b o ti c s s y st e m s w h i c h a r e c o n tr o l le d a n d c o m m a n d e d b yp l a n n i n g s u b s y s t e m b a s e d o n s e n s o r y - m o s t l y v i s u al - d a t a .

2 A G e n e r a l S t r u c t u r e

A s i m p l i f i c a t io n o f a v e r y g e n e r a l vi e w o f t h e n e r v o u s s y s t e m i n t e r m s o f c o m p u t e r

a n a l o g u e s p r o p o s e d b y M c C u t ! o c h a n d S u t r o [9] is s h o w n i n fi g u r e 1. T h o u g h



354

this really simplifies their original proposal, it has the considerable advantage

that each one of the large components shown has very concrete counterparts in

modern artificial intelligence and robotics.

First, the overall system presents a set of "modes of behaviour" tha t mimicthe accepted model of behaviour of the vertebrates [2] [3]. The selection of a

particular mode is performed by the command and control system, based mostly

in present sensorial information (S.D.) and the sta tus of the system. An external

input (E.I.) is allowed from the external world (in practice, it comes from an

operator's console) to modulate the selection of a mode.

Information concerning the selected mode (M) is sent to the sensors, which

are to be tuned to optimize the data acquisition pertinent to the mode of ac-

tion. It is also sent to the component labeled Files of World Representations,

in which the appropriate model of the environment and of the system in the

environment is selected to be sent to the component labeled Planning in Present

World Representation. Finally, the selected mode commands and controls the

process of stablishing goals according to the mode, the process of planning and

the execution of the plan, by taking into account continuous highly processed

sensory data (S). Actualized world representations are sent back through W.R.

lines when the mode changes. There are also direct connections between sensors

and actuators (line R) which are equivalent to reflex paths. Line E provides for

high level instructions to the effectors according to the plan of action, which are

to be decoded into concrete motor-effector actions.

An appropriate computer architecture to embody such a system, according

to present day technologies, is shown in Figure 2. There are two types of special-

ized processors concerning the sensory data and concerning the effectors, which

hung on the corresponding buses. Command and control, as well as planning is

performed by the Kernel, while computations corresponding to models of the

environment are performed in the unit labeled C.M.E. (Computer Models of the

Environment).

3 C om m a n d a nd C on t r o l

The basic function of a command and control system is to commit the whole

system to one overall mode of behaviour belonging to a not very large set. This

is what enables it to behave as an well-integrated unit instead of a loose connec-

tion of separate sensors, effectors and processors. In this sense, a command and

control computer is a close paradigm to the operation of the reticular formation

in vertebrates [4]. Any modes of behaviour is incompatible with any other. Some

general properties can be stablished for such a computer. First, it receives rel-atively unprocessed information from all of the sensors situated in sensory and

effector sub-systems. Second, it gives signals, which control, tune and set the

filters of all external inputs. In McCulloch words [2], "this is the structure that

decides what to look and having looked, what to heed". It also controls all the

information flow from and to higher level computers.



3 5 5

F r o m a s t ru c t u r a l p o i n t o f v ie w , t h e c o m m a n d c o m p u t e r m u s t h a v e a m o d u l a r

a r c h i t e c t u r e , o r , a t l e a s t , it m u s t s i m u l a t e i t. T h e b a s i c id e a is t h a t a s e t o f

c o m p u t i n g u n i ts ( C . U .) i s s u c h t h a t e a c h c o m p u t i n g m o d u l e r e c e iv e s i n f o r m a t i o n

o n l y f r o m a r e d u c e d p a r t o f t h e o v e r al l, li t tl e p r o c e s s e d s e n s o r y i n p u t s .E a c h c o m p u t i n g u n i t is c a p a b l e o f b o t h g e n e r a l d ia g n o s t i c s a b o u t o v e r a l l

i n p u t s i t u a t i o n s a n d o f s p e c i al iz e d d i a g n o st i c s a c c o r d i n g t o t h e v a l u e s o f a c o n c r e t

s u b s e t o f t h e i n p u t l i n e s.

A c r u c i a l p o i n t is t h a t a c o n s e n s u s o f t h e d i a g n o s ti c s - w h i c h c o r r e s p o n d s t o

t h e s e l e c ti o n o f a s in g le m o d e o f b e h a v i o u r - m u s t b e r e a c h e d b y t h e c o m p u t i n g

u n i t s i n a r e l a t i v e l y s h o r t t i m e . T h i s r e q u i r e s a v e r y s t r o n g c r o s s t a l k a m o n g

t h e c o m p u t i n g u n i t s , w h i c h is a p e c u l i a r f e a t u r e o f t h e s o - c a l l e d c o o p e r a t i v e

p r o c e ss o r s [ 4 ]. T h e r e a r e t w o b a s ic p r o p e r t ie s o f t h e c o m p u t i n g m o d u l e s t h a t

c a n b e s t a t e d e a si ly b y m e a n s o f t h e t e r m i n o l o g y c o m m o n i n e x p e r t s y s t e m .I n f a c t , w e c a n l o o k a t t h e c o m p u t i n g u n i t s a s i f t h e y w e r e s i m p li fi e d e x p e r t s

s y s t e m s w o r k i n g o n t h e i r o w n d a t a b a s e s a n d w i t h t h e i r o w n i n f e r e n c e e n g i n e s o n

t h e i r s p e c i a li z e d d o m a i n o f se n s o r y in p u t s . B u t t h e y a r e c a p a b l e a l s o o f g i v in g

u p b e f o r e t h e e v i d e n c e in d i a g n o s ti c s b y o t h e r u n i t s, w h i c h s h o w t o h a v e m o r e

r e l e v a n t in f o r m a t i o n fo r t h e c a s e . T h i s " g i v i n g u p " m u s t b e u n d e r s t o o d i n t h e

s e n se o f a r e c r u i t i n g o f t h e r e s t o f t h e m o d u l e s b y t h o s e h a v i n g m o r e c o n f i d e n c e

a b o u t t h e i r d i a g n o s t ic . A s i t w a s s t a t e d b y M c C u l l o c h s o m e t w e n t y y e a r s a g o [2],

m o d u l e s h a v i n g t h e i n f o r m a t i o n p e r t in e n t t o t h e c a se " c r y l o u d e r " , a n d d o i n g

s o, t h e y r e c r u i t t h e r e s t . T h e r e s u l t o f t h i s s t r o n g e r o s s t a l k is t h a t t h e s y s t e mc o n v e r g e s i n t o o n e m o d e , i n t h e s e n s e t h a t p r a c t i c a l l y a ll t h e u n i t s d e c i d e t h e

s a m e m o d e o f b e h a v i o u r , t h o u g h w i t h p e r h a p s d i f fe r e n t d e g r e e o f c o n f i de n c e .

M o d u l a r i t y a n d d i v is i on o f e x p e r t i s e , w i t h o v e r l a p p i n g , a m o n g t h e c o m p u t e r s

u n i t s a r e t h e t w o b a s i c f e a t u r e s o f a c o o p e r a t i v e p r o c e s si n g s y s t e m . A l s o , a p p r o -

p r i a t e c r o s s t a l k r u l e s a r e t h e n e c e s s a r y a d d e n d u m t o a c h i e v e c o n v e r g e n c e . T h i s

a r c h i t e c t u r e is s u p p o s e d t o p r o v i d e f o r t w o m a i n g o al s: f ir s t, t o s p e e d u p t h e

d e c is i o n p r o c e s s b y w h i c h a m o d e o f b e h a v i o u r is s e le c te d ; s e c o n d , t h e s y s t e m

i s s u p p o s e d t o p r e s e n t h i g h r e l i a b i l i t y , i n s u c h a w a y t h a t i t w i l l a r r i v e i n t o a n

a p p r o p r i a t e e o n s en s e d m o d e , e v e n w h e n s o m e o f t h e e x p e r t u n i t s a r e d e s t r o y e d .T h i s s e c o n d a s p e c t , t h a t is , t h e r e l ia b i l it y i n tr i n si c t o d i s t r i b u t e d e x p e r t i s e ,

p r e c l u d e s a n y d e c i si o n b a s e d u p o n a s in g le m a j o r i t y o r g a n , b e c a u s e i t s m a l f u n c -

t i o n w i ll i m p l y t o t a l i n o p e r a t i v il y . T h a t is , t h e c o n c l u s io n t h a t a c o n s e n s u s h a s

b e e n r e a c h e d c a n n o t b e t h e o u t p u t o f a n y s p e c i a l t e s t i n g u n i t r e c e i v i n g it s in -

p u t s f r o m t h e e x p e r t u n i ts . I n s t ea d , t h e d e c i d e d m o d e s m u s t b e a p p r o p r i a t e l y

l a b e l e d a c c o r d i n g t o th e i r p r o c e d e n c e t o p r e v e n t m i x i ng , a n d b e p r e s e n t i n a

n o n - c o m p u t i n g s t r u c t u r e , t h a t is , a s e t o f w i r e s - o r a x o n s- o r , i n o t h e r w o r d s , in

a k i n d o f d e c i s io n b u s .

F r o m t h i s , it b e c a m e s c l e a r t h a t r e a c h i n g a r a p i d c o n s e n s u s in t h e m o d e o fb e h a v i o u r a t t h e c o m m a n d a n d c o n t ro l c o m p u t e r is ab s o l u te l y n e c e ss a r y f o r t h e

r e s t o f t h e s y s t e m t o o p e r a t e c o h e r e n t l y , b e c a u s e , o t h e r w i s e , t h e v a r i o u s h i g h e r

a n d l o w e r s u b s y s t e m s t o b e c o n t r o l le d , w il l h a v e a h i g h p r o b a b i l i t y o f p i c k i n g u p

o p e r a t i o n i n s t r u c t i o n s f r o m t h e d e c is io n b u s, w h i c h b e l o n g t o d i f f e re n t e x c lu s i v e

m o d e s o f b e h a v i o u r , s u c h t h a t a k i n d o f n e u r o t i c s i t u a t i o n w i ll b e c r e a t e d .



356

I n s u m , t h e r o l e o f t h e c o m m a n d a n d c o n t ro l c o m p u t e r i s t o s e n se c r u d e

s e n s o ri a l d a t a , a n d t o d e c i d e m o d e s o f b e h a v i o u r s e n d i n g t h e m t o t h e d e c is i o n

b u s , t h r o u g h a s t r o n g c r o s s t a l k a m o n g u n i t s t o c o n v e r g e i n t o a s i n g le m o d e , s o

t h a t c o h e r e n t b e h a v i o u r i s s e c u r e d .

4 M u l t i s e n s o r i a l E n v i r o n m e n t R e p r e s e n t a t i o n

T h e r e a r e t w o b a s ic w a y s t o s t r u c t u r e m u l t i s e n so r i a l in f o r m a t i o n w h i ch , i n tu r n ,

a d m i t d i f fe r e n t le v el s o f r e p r e s e n t a t i o n , f o r m g e o m e t r ic t o h i g h l y s y m b o l i c , a t

l e a s t fo r a r t i f i c i a l sys t ems . These tw o w ays have a co r re l a t e w i th t he f i na l i t y

o f t h e r e p r e s en t a ti o n w h i c h m a y t e n d t o b e o p t i m a l f o r d i sc r im i n a t in g a m o n g

e n v i r o n m e n t p a t t e r n s o r t o b e r e p r e s e n t a t io n t o o p t i m i z e t h e a c q u i s i ti o n o f c l u es

f o r a c t io n s . T h e s e c o r r e s p o n d t o :a ) I n t e g r a t e d r e p r e s e n t a t i o n , b o t h a t l o w l ev e ls o f a c q u i s i ti o n a n d a h i g h l e ve l

o f th e p r o c e s s in g o f s e n s o r y d a t a .

b ) S t e p b y s t e p r e p r e s e n t a t io n , i n w h i c h i n te g r a t i o n o n l y o c c u r s a t h i g h l ev e ls

- tha t i s i n symbol i c s t ruc tu re s .

I n o t h e r w o r d s , a n d p u t t i n g a s id e f o r t h e m o m e n t a l l n a t u r a l s y s t em s , w e

m a y e i t h e r r e p r e s e n t t h e s e n s e d e n v i r o n m e n t b y m e a n s o f a m u l t id i m e n s i o n a l

s p a c e w h e r e a ll s e n s o r y m o d a l i ti e s a r e p r e s e n t w i t h t h e i r o w n r e s o l u ti o n a t l o w

level , w h i l e a l l h igh l evel p roce ss ing i s pe r fo rm ed d i rec t l y i n t h i s space . O r w e can

c o n s t r u c t a h i g h l e v el i n te r s en s o r ia l r e p r e s e n t a t i o n s p a c e b y p r e v i o u s l y e x t r a c t i n gprope r t i e s ; c l a s s i fy ing and l abe l ing each sensory moda l i t y sepa ra t e ly . These tw o

op t ions a re i l l u s t ra t ed i n f i gu re 4 (a ) and 4 (b ) .

Th ese tw o poss ib i li t ie s s eem to coex i s t i n t he h igh ly pa ra l le l co m pu t ing s t ruc -

t u r e s o f n a t u r a l s y s t e m s . T h u s , w h e n t r y i n g t o e x p l a i n t h e s t r o n g d i s c r im i n a t i n g

p o w e r o f t h e n e r v o u s s y s t e m a t h i g h r e c o g n i t i o n a n d p e r c e p t i o n l e ve ls , i t s e e m s

l o g ic a ll y n e c e s s a r y to a d m i t t h a t a k i n d o f i n t e g r a t e d r e p r e s e n t a t i o n is p re s e n t ,

because l ow l eve l , a lmos t p r ima r i l y sensed c lue s - l i ke a p i t ch o r a co lour - a re

de f in i t e c lue s t o i den t i fy h igh l eve l s i t ua t i ons . A nd a l so , t he re a re ve ry fa s t r e -

s p o n s e s o f n a t u r a l s y s t e m s b e f o r e k e y o v e ra l l i n t e r n a l- e x t e r n a l s i t u a t io n s t h a tc a n n o t b e e x p l a i n e d if e l a b o r a t e c o m p u t a t i o n i n m u l t i s en s o r i a l r e p r e s e n t a t io n

s p a c e s w h e r e r e q u i r ed . I n a n y c a s e , i t s e em s t h a t t h e t w o c o e x i s t in g m e c h a n i s m s

h a v e a t y p e o f p r i n ci p le o f c o n s t a n c y , i n t h e s e n s e t h a t i n c r ea s i n g o n e o f t h e m

i m p l ie s d e c r ea s i n g t h e o t h e r . A m o r e d e t a il e d t r e a t m e n t o f s a i d m e c h a n i s m s w a s

pre sen ted in [5 ] .

T h e a b o v e d u a l i t y is, in f a ~t , e m b o d i e d i n th e p r o p o s e d g e n e r a l s t r u c t u r e o f

f i g u r e 1 . T h u s , t h e c o m m a n d a n d c o n t r o l c o m p u t e r w i l l o p e r a t e o n d a t a w h i c h

f o ll o w t h e r e p r e s e n t a t i o n s c h e m e o f f ig u r e 4 ( b ) , w h i l e t h e F i le s o f W o r l d R e p -

r e s e n t a t i o n s , a n d , s u b s e q u e n t l y , t h e P l a n n i n g S y s t e m s , o p e r a t e a c c o r d i n g t h es c h e m e o f f ig u r e 4 ( a ) . T h i s i m p l ie s t h a t , w h e n s e t ti n g t h e m o d e o f o p e r a t i o n ,

d i f fe r e n t s e n s o r y m o d a l i ti e s a r e t a k i n g s e p a r a t e l y t h e t a s k o f e x t r a c t i n g m e d i u m

l ev e l d e s c r i p to r s , w h i c h a r e n e c e s s a r y f o r t h e o p e r a t i o n o f t h e c o m m a n d a n d

c o n t ro l c o m p u t e r . B u t , o n c e t h e m o d e i s d e c i d ed u p o n , r e p r e s e n t a t io n a n d p l a n -

n i n g s t r u c t u r e s s h a l l t a k e a g a i n t h e s e n s o r y d a t a w i t h o u t m u c h p r o c e s s i n g t o



357

" n a v i g a t e " i n a m u l t i s e n s o r i a l s p a c e w h e r e t o p e r f o r m p r o c e s s e s, f r o m l o w l e ve l s

t o h i g h l e v e l s .

T h i s i n t e r p r e t a t i o n i n c id e s u p o n t h e o l d p r o b l e m o f h o w t h e n e r v o u s s y s t e m is

c a p a b l e o f s h a r in g h i g h l ev e l c o m p u t i n g s t r u c t u r e s a f t e r d e p r e s io n o r d e s t r u c t i o no f p r i m a r y s e n s o r y c h a n n e l s [ 4] . T h a t i s, t h e s o c a ll e d in t e r s e n s o r i a l t r a n s f o r m a -

t io n s c a n o n l y o c c u r i n a n i n t e g r a t e d r e p r e s e n t a t i o n s p a c e s u c h o f t h a t i n t h e f i re

4 ( b ). T h e r e f o r e , t h e c o m m a n d a n d c o n t ro l c o m p u t e r i n n a t u r a l s y s t e m s h a v e

n o t t h e a b i l i ty t o u s e d i r e c t l y t h e e x p e r t i s e o f c o m p u t i n g u n i t s a c t i n g u p o n s e n -

s o r y d a t a w h i c h a r e d e p r e ss e d , w h il e i n t h e p l a n n i n g a n d r e p r e s e n t a t i o n s p a ce s ,

t h i s i s a p o s s i b i l i t y . I n o t h e r w o r d s , t h e r e s e e m t o b e t w o d i f f e r e n t m e c h a n i s m s

f o r a t t a i n i n g r e l i a b i li t y a n d s p e e d i n g u p a d e c is i o n a n d / o r r e c o g n i t i o n . T h a t i s,

t h e c o m m a n d a n d c o n t r o l s y s t e m o p e r a t e s w i t h e x p e r t u n i t s w h i c h re c e iv e v e r y

r e s t r ic t e d d a t a , w h i le th e p l a n n i n g a n d h i g h e r s tr u c t u r e s h a v e g e n e r a l p u r p o s e

u n i t s w h i c h m a y w o r k o n a l m o s t r o w d a t a f o r m d i f fe r en t s o u rc e s.

5 I n t e r s e n s o r i a l T r a n s f o r m a t i o n s

I n t e r se n s o r i a l T r a n s f o r m a t i o n s r e f e r t o t r a n s f o r m a t i o n s b e t w e e n d i ff e re n t s e n s o r y

m o d a l i ti e s s u c h t h a t p a t t e r n s b e l o n g in g t o o n e se n s o r y m o d a l i t y c o u l d b e , u n d e r

c i r c u m s t a n c e s , h a n d l e d a n d " r e c o g n i z e d " b y c o m p u t i n g s t r u c t u r e s w h i c h b e l o n g

t o a d i f f e re n t s e n s o r y m o d a l i t y .T h e f i r s t r e q u i s i t e is t o t r a n s f o r m t h e o r i g i n a l s e n s o r y d a t a t o c u a s i - g e o m e t r i c a l

r e p r e s e n t a t i o n s p a c e s . I n a r t if ic i a l s e n s o r y s y s t e m s w e c a n t h i n k o f a v a r i e t y o f

i n s t a n c e s o f h o w a r e p r e s e n t a t i o n s p a c e c a n b e c o n s t r u c t e d , f o r v i s u a l o r fo r

o t h e r i n p u t . F r o m e a c h r e p r e s e n t a t io n , s p a c e m e c h a n i s m s a c t i n g as " o p e r a t o r s "

o n t h e s p a c e , p r o v i d e f o r o u t p u t s c a r r y i n g s o m e t y p e o f d e c i si o n o r c la s si fi ca -

t io n s , w h i c h a r e r e q u i r e d f o r t h e o v e r a l l d i a g n o s is o f t h e s e n s o r y s i t u a t i o n . T h i s

o v e r al l o u t p u t e n t e rs a " s e n s o r y i n t e g r a ti o n " p r o c e ss , t o p r o d u c e t h a t o v e r a l l

d i a g n o s is , b y a p p l y i n g s o m e d e c is i o n r u l e s w h e r e t h e " b l a n k s " i n t h e r u l e s a r e t o

b e f i ll ed w i t h t h e d a t a p r o v i d e d b y e a c h s e n s o r y m o d a l i ty . I n t e r s e n s o r ia l t r a n s -f o r m a t i o n s " a c t " a m o n g t h e r e p r e s e n t a t i o n s p a c e s , t h a t i s , i n t e r c o n n e c t t h e m .

W e s h a l l m a k e v a r i a t i o n s o n t h i s .

A s f o r t h e c e n t r a l n e r v o u s s y s t e m , i t is c le a r t h a t s p e c if ic s e n s o r y p a t h w a y s

b e c a m e m u l t if u n c t i o n a l a s t h e y p r o c e e d u p w a r d s t o w a r d m o r e c e n t r a l a re a s , i n

s u c h a w a y t h a t s t r u c t u r e s w h i c h a r e s p e c if ic c a n , u n d e r c i r c u m s t a n c e s b e u s e d

b y d i f fe r e n t s e n s o r y m o d a l i ti e s . T h i s i s s o i n e m e r g e n c y s i tu a t i o n s , e .g . u n d e r

t r a u m a t i c l es io n s . I n o t h e r w o r d s , f u n c t i o n a l s p e c i f ic i ty is le ss d o g m a t i c a n d

m o r e c i r c u m s t a n t i a l a s m o r e c e n t r a l z o n e s a r e c o n s i d e r e d i n a s e n s o r y p a t h w a y .

T h i s c h a r a c t e r i s ti c m u s t b e t a k e n i n t o a c c o u n t w h e n t h e h i g h d e g r e e o f r e l ia b i l i tyo f n e r v o u s t i s s u e i s t o b e e x p l a i n e d .

A s i m p l i fi e d r e p r e s e n t a t i o n o f v a r i o u s m e d i u m l ev e l s e n s o r y c o r t e x f u n c t i o n s ,

a s t h e y a r e n o r m a l l y a c c e p t e d i n b r a i n t h e o r y , is p r e c i s e ly t h a t s h o w n i n f i g u r e

4 . b. H e r e a t y p i c a l p r o c e s s o f s e n s o r y i n t e g r a t i o n i s r e p r e s e n t e d , w h i c h g o a l s a r e

t h e d i a g n o s t i c s o f a n o v e r a l l e x t e r n a l s e n s o r y s i t u a t i o n .



358

Sensory dat a form each modality is preprocessed in specific pathways, before

they reach the cortex, in a way such that a translation to a specific symbolic lan-

guage takes place. This language is the one understood by the processors at the

primary sensory cortex. It is important to point tha t the messages being trans-mit ted to the primary sensory cortex are already represented in a language which

probably is much more complex that the usual pulse code normally accepted in

neurophysiology. Primary sensory cortex classifies and labels the corresponding

sensory apparitions. This classification and labeling are a consequence of map-

ping in representation spaces and of applying classification and decision rules,

which are either acquired by learning or built-in. One of the implicit properties

which are normally ascribed to primary sensory cortex processors is their almost

total specificity, in a way such that practically no possible intersensorial trans-

formation takes place, but just a posterior multisensorial integration to converge

in the overall diagnosis.

This is a consequence of admitting that the crucial mechanism to attain

diagnoses convergence is a high level multisensorial integration, with no previous

intersensorial talk. From the behavioral point of view, multisensorial integrat ion

can be thought to be directed towards two essential goals: a) to accelerate and

optimize in time and resources, the diagnostic and identification process, by

means of the use of intersensorial clues (that is, labels which, by learning or

instinct, are associated to belong to a same extern-internal global situation), b)

To separate classes of situations, which are not separable by means of a single

sensory modality, so increasing the discriminating power of the sensory system.

The diagram of figure 4.b fulfills the requirements corresponding to the above

goal. Obviously, this diagram can be sophisticated by adding a series of refine-

ments in the processors corresponding to primary sensory cortex and to associa-

tive or integrating cortex, such as a sensory model of the environment, expressed

in a more or less abstract language. Also, the existence of centrifugal (feedback)

pathways can be included to adapt the resolution and subsequent computational

costs of the processors. The concepts of intersensorial transformation permit,

however, a qualitative change in said diagram.If we assume that a lesion in the specific pathways happens, according figure

4.b., the processors corresponding to the primary sensory cortex will became

out of use, since there are no inputs. However, the experiments of J. Gonzalo [7]

show that is not stric tly the case. That is, the practical absolute specificity of the

processors in the primary sensory cortex tends to disappear in the case of lesion

of the specific afferents, after a learning process. Also, the drawbacks, which re-

sult from primary sensory cortex lesions, can be diminished after training, such

that the eliminated function is partly assumed by the remaining cortical struc-

tures. The above can, in principle, be expressed in terms of a global behavioralgoal, as it was done for multisensorial integration. The assumption is as follows.

There exists and adaptive sharing of the specific st ructures of different sensory

modalities, such that, after learning, intersensorial information can be utilized to

increase reliability and to tend to optimize the use of the structures which remain

after lesions or when there is a low information input to a sensory pathway.



359

A p o s s i b le s y s t e m s s o l u t io n i s d i a g r a m m e d i n F i g u r e 5 . I n t e r s e n s o r i a l t r a n s -

f o r m a t i o n s I T o c c u r b e t w e e n t h e p r o c e ss o r s s p ec if ic t o e a c h s e n s o r y m o d a l i t y .

T h e r e a r e t w o c a s es i n w h i c h , c o m p u t e r w i s e , w e m a y t h i n k o f i n t e r s e n s o r i a l

t r a n s f o r m a t i o n s c o m i n g i n t o p l a y : 1 ) W h e n t h e r e i s a n o v e r fl o w o f s e n s o r y i n f o r-

m a t i o n f r o m a s e n s o r y p a t h w a y ( A ) t o t h e i r m o r e c e n t r a l sp e c if ic p r o c e s so r s , a n d

t h e r e a r e d i m e n s i o n s w h i c h a re f re e ( n o n u t i li z e d ) i n t h e r e p r e s e n t a t i o n s p a c es o f

o t h e r s e n s o r y m o d a l i t i e s ( B , C ) . T h i s o v e rf lo w m a y a p p e a r a s a c o n s e q u e n c e o f a

t r a u m a t i c r e d u c t i o n i n t h e s p ec if ic p r o c e ss o r s f u n c t i o n a l i t y o f (B , C ) . T h e t r a n s -

f o r m a t i o n p r o c e e d s f ro m ( A ) t o ( B , C ) . 2 ) W h e n , b e c a u s e a t r a u m a t i c l e si o n o r

c i r c u n s t a n c i a l e f fe c ts , t h e r e i s a l ow s e n s o r y f lo w f r o m t h e s e n s o r y p a t h w a y s o f

a m o d a l i t y ( A ) , w h i c h f r e e d i m e n s i o n s i n t h e i r r e p r e s e n t a t i o n s p a c e . T h e s e f r e e

d i m e n s i o n s c a n b e o c c u p i e d b y d a t a t h r o u g h t r a n s f o r m a t i o n s f r o m o t h e r s e n -

s o r y m o d a l i t i e s ( B , C ) . A n d a l s o , t h e r e a r e c o m p u t e r w i s e p o s s i b i l i t i e s t o d e f i n e

i n t e r s e n s o r i a l t r a n s f o r m a t i o n s a m o n g r e p r e s e n t a t i o n o r " f e a t u r e s " s p a c e s . B u t

i n p u r it y , w h e n t a lk i n g a b o u t b r a i n s, a n d n o t a b o u t r o b o t s , t h e a b o v e m u s t b e

t a k e n a s m e t a p h o r s .

6 P l a n n i n g

P l a n n i n g t a k e s p l a c e i n a w o r l d r e p r e s e n t a t i o n s c e n a r y o r s t a g e , w h i c h c o r r e -

s p o n d s t o t h e s e l e ct e d m o d e o f b e h a v i o u r . I t i s u s e fu l t o c o n s i d e r t h a t t h i s m a yb e p e r f o r m e d a t v a r i o u s l ev e ls o f s e n s o r y d a t a e l a b o r a t i o n . T h e q u e s t i o n o f g e n -

e r a t i n g p l a n s f o r c o m p l e x p r o b l e m s o l v i n g a s a m a t t e r o f a r t i f i c ia l i n t e l l ig e n c e

t e c h n i q u e s , s u g g e s t s tw o p r a c t i c a l- a r ti f ic i a l p r o b l e m d o m a i n s t h a t a r e o f i m m e -

c ii at e u s e. F i r s t , t h e r e i s t h e p r o b l e m o f m o v i n g s o li d s h a p e s t h r o u g h a r e s t r i c t e d

wor ld , a nd se c ond , the r e i s p l a nn ing in b loc ks wor ld [ 1 ] [ 6 ] .

T h e f i r st p r o b l e m d o m a i n is v e r y cl os e t o t h a t o f n a v i g a t i n g a r o b o t b y

a v o i d i n g o b s t a c l es , a n d i t is b a s e d o n a s c e n a r y w h o s e r e p r e s e n t a t i o n m a y b e

g e o m e t r i c - l i k e , h a v i n g l o w s y m b o l i c c o n t e n t . T h e s e c o n d p r o b l e m d o m a i n m a y

c o n t a i n s y m b o l i c s c e n a ri e s a n d t h e p l a n n i n g b e p e r f o r m e d a t h i g h e r l e ve ls .T h i s s u g g e s t s a f ir s t d i c h o t o m y i n p l a n n i n g t h a t c a n b e c a s c a d e d u n d e r c o i n -

m a n d a n d c o n t r o l o f t h e s e le c te d m o d e o f b e h a v i o u r , a s it i s i l l u s t r a t e d i n F i g u r e

6 .

P l a n n i n g o n t h e l ow - le v el s c e n a r y c a n b e f o r m u l a t e d i n q u a s i - g e o m e t r i c t e r m s .

T h e s c e n ar y , it s e lf i s, in m o s t o f c a se s , d e t e r m i n e d b y a s e t o f a n i n d e p e n d e n t

v a r ia b l e s, d e f i n i n g a " s p a c e " , p l u s a n u m b e r o f r e s t r i c t e d z o n e s . T h e s e r e s t r i c t io n s

a r e v o l u m e s V i , w i t h d e c i s io n ru l e s d e fi n i n g t h e m e m b e r s h i p t o V i f o r a n y p o i n t

o f t h e s p a c e . O b j e c t s a r e s e ts o f p o i n t s P 1 . .. P N n o t b e l o n g i n g t o V i w h i c h a r e

s u b j e c t e d t o K r e l a ti o n s R K ( P i) . G e n e r a t i n g a p l a n c o n s i s ts e s s e n ti a l ly i n fi n d i n gt r a j e c t o r i e s f o r P i , i n a g r e e m e n t w i t h r e s t r i c t i o n s a n d r e l a t i o n s , u n d e r a " g o a l

f i e ld" .

A t h i g h e r l e v e l s , p l a n n i n g c a n b e s t a t e d i n a s i m i l a r w a y , b y a p p r o p r i a t e l y

c h a n g i n g t h e l ev e l o f si g n i fi c a ti o n o f t h e c o n c e p t s , a n d s u b s e q u e n t l y d e f i n i n g t h e

r u l e s f o r h a n d l i n g s c e n a r i e s , o b j e c t s , g o a l f i e l d s a n d t r a j e c t o r i e s .



360

7 C o n c l u s i o n

T h e i n t e g r a t e d v i ew o f a s y s t e m d i s p l a y i n g n o n t r i v i a l a r t if i ci a l b e h a v i o u r r e -

q u i re s t h e i n c lu s i o n , a t l e a st , o f t h e g e n e r a l c o m p o n e n t s d e s c r i b e d i n p r e c e d e n ts e c ti o n s . T h e p r o p o s e d g e n e r a l s t r u c t u r e i s c o n c r e t e e n o u g h t o b e o f p r a c t i c a l

r e a li z a b il i ty . D e v e l o p m e n t o f t h e d e t a i l s o f t h e s t r u c t u r e a n d f u n c t i o n s o f t h e

c o m p o n e n t s a s w e l l a s t h e c o m m u n i c a t i o n s is a r e se a r c h u n d e r w a y , t o b e a p -

p l ie d t o p r a c t i c a l v i s u a l r o b o t s y s t e m s .

R e f e r e n c e s

1. Brooks , R . , L ozano-Perez, T . : A Subdivis ion Algo r i thm Con f igura t ion Space for

F indpa th wi th Rota t ion . Proc . Eight I JCAI , A. Bondy, de . Los a l tos , Ca l i f . : W.Kauffam. (1983) 799-806

2. Ki lmer , W . , McCul loch, W .S. : The Ret icula r Form at ion Co m m and and Con tro l Sys-

tem . In: Info rm atio n Processing in the N ervous Sy stem . K.N . Leibovic , ed. Berl in,Heidelberg, New York: Springer. (1969) 297-308

3. Ki lmer , W. : A G loba l Imh ibi tory Model for Dec id ing Mod es of At ten t ion . In Bra inProcesses, T heories and Models. R.Moreno-Diaz, J .M ira-M ira , eds. The M IT Press.

Cambridge MA. (1996) 125-1334. M ira , J . , Delgado , A.E. , Manjaros, A. , Ro s, S. , Alvarez, J .R. : C oop erative Processes

a t the Sym bol ic leve l in Cerebra l D ynam ics : Re l iabi l i ty an d F aul t Tole rance . In

Bra in Processes, Th eories an d Models. R. Moreno-Diaz, J .M ira-M ira , eds. Th e M ITPress, Cambridge MA. (1996) 244-255.

5 . Moreno-Diaz , R . , M ira, J . : Conceptos para u na teor ia de la in tegrac ion mul t i senso-

rial. Proc. II Simpos. Nac. IFAC. Zaragoza, Spain: Universidad (1984) 227-232

6. Nilson, N .J.: P rincip les of A rtificial Intelligence. Pa lo A lto, Calif ." Tio ga. (1980)7 . S ut ro , L .L. , W arren , R .E. , Mou l ton , D. , W hi tm an , C . , Ze ise, F . : 1963 Ad vanced

Sensor Inves t iga t ions I{-470. Ins t rum enta t ion Lab ora tory . Cam br idge , MASS: M IT.

(1964)8 . Sut ro , L . , Ki lm er , W . , McCul loch, W .S . , Ca tchpole , R . , Tweed, D. , Blum , J . , Pe te r -

son, D. , Morenc~Diaz, R. : Sensory, Decision and Control Systems. R-548. Instru-

m e n ta t ion La b or a to r y . C a m br idge , M AS S : M I T (1966)9 . S u t r o , L ., K i lm e r , W . : Asse m bly o f C om pute r s to C om m a nd a nd C on t r o l a R obo t .

1{-582. Ins t ru m enta t ion Labo ra tory . Cam br idge , MASS: M IT (1969)

Documents

SPRINGERLINK SISTEMAS INTELIGENTES