Swarm Intelligence - techrepublic

pillowfistsAI and Robotics

Nov 13, 2013 (3 years and 10 months ago)

118 views

SWARM INTELLIGENCE

Sumesh Kannan

Roll No 18

Introduction


Swarm intelligence (SI) is an artificial intelligence

technique
based around the study of collective behavior in decentralized,
self
-
organized systems.



Introduced by Beni & Wang in 1989.



Typically made up of a population of simple agents.



Examples in nature : ant colonies, bird flocking, animal herding
etc.


Intelligent Agents


An
agent
is anything that can be viewed as
perceiving
its
environment through
sensors
and
acting
upon that
environment through
effectors
.

Rational Agents


Rationality
-

expected
success
given what has been perceived
.



Rationality is not omniscience.



Ideal rational agent should do whatever action is expected to
maximize its performance measure, on the basis of the
evidence provided by the percept sequence and whatever
built
-
in knowledge
the agent has.



Factors on which Rationality depends


Performance measure

(degree of success).


Percept sequence

(everything agent has perceived so far).


Agents knowledge

about the environment.


Actions

that agent can perform.



Structure of IA


Agent = Program + Architecture



A Simple Agent Program.

Simple Reflex Agents


Follows
Condition
-
Action Rule.



Needs to perceive its environment completely.

Model Based Agents


Need not perceive the environment completely.



Maintains an
internal state
.



Internal states should be updated.

Goal Based Agents


Makes decisions to achieve a goal.



More flexible.

Utility Based Agents


A complete specification of the utility function allows rational
decisions in two kinds of cases.


Many goals, none can be achieved with certainty.


Conflicting goals.

Environment


Accessible vs. Inaccessible



Deterministic vs. Non
-
deterministic



Episodic vs. Non
-
episodic



Static vs. Dynamic



Continuous vs. Discreet

An Environment Procedure

Ant Colony Optimization (ACO)


First ACO system
-

Marco Dorgo,1992



Ants search for food.



The shorter the path the greater the pheromone left by an ant.



The probability of taking a route is directly proportional to the
level of pheromone on that route.



As more and more ants take the shorter path, the pheromone
level increases.



Efficiently solves problems like vehicle routing, network
maintenance, the traveling salesperson.

Particle Swarm Optimization (PSO)


Population based Stochastic optimization technique.



Developed by Dr. Eberhart & Dr. Kennedy in 1995.



The potential solutions, called particles, fly through the
problem space by following the current optimum particles.



Applied in many areas: function optimization, artificial neural
network training, fuzzy system control etc.

Swarm Robotics


Most
important application

area of Swarm Intelligence



Swarms provide the possibility of enhanced task performance,
high reliability (fault tolerance), low unit complexity and
decreased cost over traditional robotic systems



Can accomplish some tasks that would be impossible for a
single robot to achieve.



Swarm robots can be applied to many fields, such as flexible
manufacturing systems, spacecraft, inspection/maintenance,
construction, agriculture, and medicine work



Applications


Massive (Multiple Agent Simulation System in Virtual
Environment) Software.


Developed Stephen Regelous for visual effects industry.




Snowbots


Developed Sandia National laboratory.

References

http://en.wikipedia.org


http://www.swarmbots.com


http://www.siprojects.com






Thank you