Artificial Intelligence in Real-time Systems

imminentpoppedAI and Robotics

Feb 23, 2014 (3 years and 5 months ago)

71 views

23.02.2014

1

Artificial Intelligence

in Real
-
time Systems

LAP 8780 and ISP 9010

Tallinn University of Technology

Professor Leo Motus

23.02.2014

©L.Motus, 2004

2

J. McCarthy “What is Artificial
Intelligence” (November 2004)


science and engineering of making intelligent
machines, especially computer programs; need not
confine itself to methods that are biologically
observable.


Intelligence is the computational part of the ability to
achieve goals in the world


AI research started after WWII. Alan Turing’s lecture in
1947


he was the first to decide that AI was best
researched by programming computers rather than
building machines


http://www.formal.stanford.edu/jmc/whatisai/


23.02.2014

©L.Motus, 2004

3

Schools of thought in AI (1)


Conventional AI

o
Expert systems

o
Case based reasoning

o
Bayesian networks

o
Behaviour based AI


Computational Intelligence

o
Neural networks

o
Fuzzy systems

o
Evolutionary computation

23.02.2014

©L.Motus, 2004

4

Schools of thought in AI (2)


Conventional AI


behaviour based AI

A methodology for developing AI based on modular
decomposition of intelligence (e.g. Rodney Brooks):

o
Robotics and intelligent agents (real
-
time
dynamic systems able to run in complex
environments


Computationally leads

to interaction
-
based model of
computation, e.g. super
-
Turing computation

See the course ISP 0012


software dynamics


23.02.2014

©L.Motus, 2004

5

Schools of thought in AI (3)


Computational intelligence


evolutionary computation

Applies biologically inspired concepts, e.g. population,
mutation, survival of the fittest. These methods divide
into two:

o
Evolutionary algorithms, e.g. genetic algorithms

o
for search and optimisation

o
Swarm intelligence, e.g. ants

o
A collective behaviour in decentralised, self
-
organised systems (e.g. multi
-
agent systems)

23.02.2014

©L.Motus, 2004

6

Examples of artificial intelligence
based techniques

(1)

Basic (algorithm
-
centred)

techniques stem from studying:

o
Representation

of shallow and deep knowledge

o
Reasoning

(problem solving), including the pattern
(or condition) matching problems

o
Learning and adaptation

(supervised and/or
unsupervised)

o
Search

(including data mining)

By combining the basic techniques more complex
problems can be solved


e.g. computer vision

The above
-
listed techniques are based on imitating
processes applied by biological creatures.

23.02.2014

©L.Motus, 2004

7

Examples of artificial intelligence
based techniques (2)

Expansion of the domain where AI techniques were
applied, and deeper understanding of the essence of
“intelligence” has lead to non
-
algorithmic techniques:

o
Agents, info
-
bots, nanobots, etc

o
Coalition of agents, multi
-
agent systems

o
Proactive components, social intelligence (?)


J. Ferber (1999) Multi
-
agent systems, Addison
-
Wesley

R. Brooks (1986) “
A robust layered control system for a
mobile robot”, IEEE J.of Robotics and Automation

23.02.2014

©L.Motus, 2004

8

Biological paradigms for Artificial
Intelligence and Real
-
time Control



Stem from the functioning principles of humans and
other biological species:

o
Hypothetical division of functions between left and
right hemisphere

o
A functional model of human brain by Newell and
Simon

o
Studies in swarm intelligence
, and
animal behaviour

o
Studies and experiments in molecular biology



23.02.2014

©L.Motus, 2004

9

Opposing characteristics of the co
-
resident brain computers


von Neumann serial
processor

(symbol
processing) is
believed to operate in
the
left hemisphere

of a human brain

Associative parallel
processor

(pattern
processing) is believed
to operate in the
right
hemisphere

of a
human brain

23.02.2014

©L.Motus, 2004

10

Comparison of functions of the
hemispheres (human brain)

The computation and/or reasoning is
:


in the left hemisphere


in the right hemisphere

-

linear




-

non

linear


-

time sequential



-

time independent


-

batch oriented



-

multi
-
tasking

-

stacked interrupts


-

random parallel execution

-

word/symbol oriented


-

pattern oriented

-

non
-
intuitive



-

highly intuitive

-

structured memory


-

associative memory


23.02.2014

©L.Motus, 2004

11

Comparison of functions of the
hemispheres (human brain)

The computation and/or reasoning is:


in the left hemisphere


in the right hemisphere


-

cumulative correlation


-

instantaneous multiple







correlation


-

incremental learning


-

non
-
sequential learning


-

sensory dependent



-

sensory independent



V. Rauzino, “ Some opposing characteristics of the Co
-
resident Brain Computers” Datamation, 1982, vol. 28,
no.5, 122
-
136

23.02.2014

©L.Motus, 2004

12

Newell
-
Simon functional model of a
human brain



Motory
actions

Cognition

Perception

Buffers

Sensors

Interpreter

Cognitive
processor

Internal memory l/s

External memory

Buffers

Human
muscles

23.02.2014

©L.Motus, 2004

13

Basic difference between conventional
AI and AI in RT systems

(1)



Technical
or natural
system

System based
on AI

1.

2.

3.

4.

Conventional AI is explicitly human centric !

23.02.2014

©L.Motus, 2004

14

Basic difference between conventional
AI and AI in RT systems

(2)



Technical
or natural
system

System based
on AI

A1

A2

H1, H2

H3, H4

Humans have just a role of a supervisor

in AI applications in Real
-
time systems !


23.02.2014

©L.Motus, 2004

15

A view on a real
-
time system



Environment

A system comprising humans, computers, etc

Task
i

Task 1

Task
2

Task
n

Task
3

23.02.2014

©L.Motus, 2004

16

A closer view on a task in a real
-
time system


Each task can be carried out by applying different
methods, e.g.:

o
Methods based on “natural intelligence “


i.e.
manually

o
Methods based on Science (e.g. mathematics,
control theory, etc)

o
Methods based on “artificial intelligence”


i.e. crisp
theory based reasoning, approximate methods of
reasoning (
e.g.
neural nets, fuzzy logic), distributed
intelligence methods (e.g. agents)


23.02.2014

©L.Motus, 2004

17

Intelligent methods

(+)

Natural and artificial intelligence based methods are good
since

they:

o
Provide efficient solution to a many computationally
complex problems

o
Decrease the burden of mathematical modelling

o
Enable to use approximate non
-
linear methods for
reducing the dimensionality of input space

o
Are capable of drawing unexpected conclusions
and applying unconventional methods on spot.

23.02.2014

©L.Motus, 2004

18

Intelligent methods (
-
)

Natural and artificial intelligence based methods are not
always applicable because:

o
Only probabilistic estimates are available for the
quality of obtained solutions (they are approximations
of the “scientific” solutions)

o
Time for obtaining a solution is indeterminate (the
case of deduction based methods)

o
Due to insufficient educational back
g
round those
methods are too often handled as “black boxes”


hence no guaranteed result

23.02.2014

©L.Motus, 2004

19

Intelligent methods


the case of
conventional AI applications


Many
independent

tasks are solved simultaneously,
or rather a single task at a time


The environment cannot influence task execution
process


truth values are independent of time and
events
,

occurring in the environment or in the other
tasks


Frequent use of backtracking


task execution time is
indeterminate


Goals and sub
-
goals of tasks are static, and are to be
fixed before the execution of the task starts

23.02.2014

©L.Motus, 2004

20

Intelligent methods


the case of AI
methods in real
-
time systems


Many, inter
-
dependent tasks are to be solved
simultaneously (forced concurrency)


The environment can influence the task execution
process


truth values may change dynamically,
depending on time and events occurring in the
environment


Time for execution of a tasks is often strictly limited


Goals and sub
-
goals for tasks may be determined
dynamically (during the task execution)


only a strategic
goal is usually fixed before the execution starts

23.02.2014

©L.Motus, 2004

21

Names used for AI methods are not
self
-
explaining and straightforward

Most of the methods and tools used have historical names
and are in
-
between of pure deductive and pure inductive
methods.

For instance, expert systems:

o
The first
-
order predicate calculus

is a typical expert
system and represents a classical deductive approach

o
First
-
generation expert systems

(e.g. the frustrated
banker) are a typical inductive approach

o
Second generation expert system

(a mixture of deep
and shallow knowledge) are in between the two
approaches

23.02.2014

©L.Motus, 2004

22

Quality of a task’s solution

In conventional AI application

quality means logical and
quantitative correctness of a solution


normally a vector
comprising, e.g. precision, risk estimate, cost, etc.

In AI application in a real
-
time system

timeliness is
added as the highest priority component of the quality
vector

Conventional quality
-
wise



more promising are
deductive methods

Time
-
wise



more promising are inductive methods

23.02.2014

©L.Motus, 2004

23

Intelligent methods


deductive
approach

Paradigm

--

top
-
down approach;



from a general case to a specific case

o
humans


build a non
-
contradicting theory, based on
deep knowledge and experimental data

o
Specific problems are stated (usually by humans) as
special cases of this theory, and then solved by
computers

Examples
: theorem provers, structural synthesis of
programs


23.02.2014

©L.Motus, 2004

24

Intelligent methods


inductive
approach

Paradigm



bottom
-
up approach;


from a specific case to a general case


o
Humans provide meta
-
theory

o
Based on meta
-
theory and a set of examples
(problems with solutions), computers (or humans)
build specific theories that resolve a class of
problems

Examples:

neural nets, inductive synthesis of programs

Note
: induction and co
-
induction

23.02.2014

©L.Motus, 2004

25

Comparing deductive and inductive
approaches

Advantages:


Deductive methods

provide guaranteed quality of the
solution, if obtained


Inductive methods

have short and rather
deterministic execution time

Disadvantages
:


Deductive methods

have indeterminate solution time
and high resource requirements

(
labour
-
consuming
)


Inductive methods

have usually unknown quality of
the solution, formation of the learning set is not easy
,
learning time is lengthy (building a special theory)

23.02.2014

©L.Motus, 2004

26

Approximate reasoning (1)

Pragmatic goals:

o
to obtain interim result in the reasoning process
before any given deadline

o
be able to continue reasoning if time and other
resources permit

Implicit assumption



the quality of the reasoning
outcome (and interim results) improve
s

proportionally
with the given time and resources


23.02.2014

©L.Motus, 2004

27

Approximate reasoning

(2)

Also known as:


imprecise computing, any
-
time algorithms, progressive
reasoning
,
etc
.

Basic idea



to make reasoning results available in time
-
deterministic way, and to continue reasoning if additional
time becomes available

See, for instance,

I.R. Chen “On applying Imprecise Computation to Real
-
time AI Systems”, The Computer Journal, vol.38, no.6,
1995, ,434


442
(
kataloog lugemisvara
)

Reflex
-
based approach


a way out

for real
-
time systems?

23.02.2014

©L.Motus, 2004

28

Approximate reasoning (
3
)

A simple example of approximate reasoning


for
e
casting
the trends based on observations:

o
Based on recursive computation of
a posteriori

probability densities

o
Based on recursive adjustment of membership
functions (possibilities), related to many
-
valued logic
and case
-
base reasoning


Approximate solution methods (Bayesian neural nets and
possibilistic neural nets) are used to reduce
computational complexities
.


23.02.2014

©L.Motus, 2004

29

Two different clusters of data for
computing a posteriori distribution



23.02.2014

©L.Motus, 2004

30

Approximate
a posteriori

probability
density computed by Bayesian

NN



23.02.2014

©L.Motus, 2004

31

Scattering is used instead of probability
density (possibilistic neural net)



23.02.2014

©L.Motus, 2004

32

Possibility distribution as computed
by a possibilistic neural net



23.02.2014

©L.Motus, 2004

33

Reflex
-
based approach to
approximate reasoning

(1)

Imitates the behaviour of biological creatures acting in hard
real
-
time



e.g.

car driving, collective games (karate,
dancing), riding a bicycle

Observation



an experienced driver makes complex and
high quality decisions in a short time, a novice driver
cannot reach such decisions (even if

given unlimited
time)

Hypothesis

--

decisions and actions of humans in hard
real
-
time are based on reflexes rather than on
conventional reasoning



23.02.2014

©L.Motus, 2004

34

Reflex
-
based approach to
approximate reasoning (2)

Reflex
-
based approach to reasoning
:

o
should combine deductive and inductive
approaches

o
leads not necessarily to an approximation of the
inference tree

o
creates shortcuts on the inference tree by modifying
inference rules, a set of axioms, or both


A weak similarity



with time deterministic case
-
base
reasoning method as used in the BRIDGE project

23.02.2014

©L.Motus, 2004

35

AI applications in Real
-
time
systems (examples)


Navigation tasks, computer vision related tasks,
performance of AUV, etc


On
-
line assessment of strategies, generation of
alternative strategies and/or goals


Coordinated work of multiple agents, especially time
-
aware agents, agent coalitions and their competition


Sensor fusion, feature fusion, remote monitoring,
safety, reliability and fault
-
tolerant problems.


The Farm project provides plenty of possibilities to study
and test additional examples

23.02.2014

©L.Motus, 2004

36

Generic groups of AI applications
in Real
-
time systems (1)

1.
Automatic generation and/or assessment

of
alternative solutions

o
Typical problems


optimisation, adaptation, self
-
learning, consistency check

2.
Dynamic knowledge presentation and integration

o
Typical problems


sensor fusion, process
monitoring and diagnosis, reliability and safety
backing, pattern forming, pattern matching


23.02.2014

©L.Motus, 2004

37

Generic groups of AI applications
in Real
-
time systems (2)

3
. Coordinated work of multiple agents

(proactive
components)

o
Typical problems


interaction of agents, multiple
goal system, dynamic change of goals, network for
interacting agents


Generic groups ordered by increasing complexity :


group 1


group 2


group 3


23.02.2014

©L.Motus, 2004

38

Characteristic issues when
applying AI in Real
-
time systems



AI based methods cannot be applied independently and
must cooperate with parts of a time
-
aware, or time
-
critical environment


Two basic goals are to be achieved


time
-
aware
behaviour and persistent assessment the quality of
service


Induction based methods create less problems time
-
wise, and more problems quality
-
wise


Deduction based methods create less problems quality
-
wise, and more problems time
-
wise


23.02.2014

©L.Motus, 2004

39

Ways of interdisciplinary integration
of AI and non
-
AI methods

(1)

1.
Mechanical combination of methods

from various
domains

o
CAD, genetic algorithms, knowledge
representation, expert systems, control theory,
software engineering, qualitative reasoning

2.
New methods based on combination of AI and
non
-
AI

theories

o

approximate solution of hitherto not applicable
mathematical problems (
Pontryagin’s maximum
principle


two
-
point boundary value problem


neural nets
)

23.02.2014

©L.Motus, 2004

40

Ways of interdisciplinary integration
of AI and non
-
AI methods

(2)

3.
Use of the abstract nature of AI methods
to clarify
the essence of problems

o
Intrinsic similarity of the design, analysis, and
verification of hardware and software design

o
Necessity to apply different methods for solving
different problems


strengths and weaknesses of
algorithm
-
centred and interaction
-
centred
computing

23.02.2014

©L.Motus, 2004

41

Additional reading on Artificial
Intelligence in Real
-
time system


Journals available in Department of Computer Control (TTU)

o
Engineering Applications of Artificial Intelligence
(Elsevier)

o
Intelligent Computer
-
Aided Engineering (IOC)

o
Real
-
time Systems


Journal of Time
-
critical Computing
(Kluwer)


Other Journals

o
Journal on Autonomous Agents and Multi
-
agent systems
(Kluwer)