Swarm Intelligence for Local Transit Revised 123

24
SWARM INTELLIGENCE FOR LOCAL TRANSIT -AMIT DHAKATE (V SEM., SEC.- A, R.NO.- 21) -PROJECT GUIDE PROF. V.M. KORDE

Transcript of Swarm Intelligence for Local Transit Revised 123

Page 1: Swarm Intelligence for Local Transit Revised 123

SWARM INTELLIGENCE FOR LOCAL TRANSIT

-AMIT DHAKATE (V SEM., SEC.- A, R.NO.-21)-PROJECT GUIDEPROF. V.M. KORDE

Page 2: Swarm Intelligence for Local Transit Revised 123

CONTENTS• Introduction: What is swarm intelligence• Background• Swarm intelligence • Multi-agent system(MAS)• Naturally occurring algorithms• Ant colony optimization• Energy Balancing Routing

in Sensor Network• Energy Balancing Routing

in Sensor Network• Particle Swarm Optimization• Conclusion

Page 3: Swarm Intelligence for Local Transit Revised 123

IntroductionSwarm intelligence is based on collective

behavior of a self-organized group of agents.The problem that is being addressed in this

seminar is transportation.This goal has two parts:

• The swarm will start at the home base & will first need to find the goal, identify it & position it path to its proper location.

• After an agent in the swarm has succeeded in finding the goal base, it gives a signal to other agent in the grid other agent finds the second goal of transporting all supplies in the home base to the goal base.

Page 4: Swarm Intelligence for Local Transit Revised 123

Background• Multi-agent systems and swarm intelligence were first

introduced by G. Beni with cellular robotics.• Swarm intelligence is one approach to solving problems

by imitating nature and, more specifically, by imitating swarms such as bees, ants, and birds.

• The significance of swarm intelligence is that each agent in the swarm is governed by a simple set of rules, but the entire swarm as a whole exhibits complex behavior.

• This also usually means that each agent does not have global knowledge of its environment nor does it have access to all knowledge of the swarm.

• It acts based on local environmental knowledge and nearby neighbors only.

Page 5: Swarm Intelligence for Local Transit Revised 123

Swarm Intelligence• There are a number of systems which seems

to exhibit swarm intelligence:− Animal colonies and specifically insect

colonies like ants, termites, and bees− Bacteria which appear able to act in a

finalized way− The Brain: intelligence and mind arises

form the interaction of simple neurons− The Cell: homeostasis and the capability

of adapting and reproducing ariseform protein interactions

• Swarm intelligence is not an “accident” but rather a property of the systems

Page 6: Swarm Intelligence for Local Transit Revised 123

Characteristics of swarm intelligent systems is often

said to be an “emergent behavior”

•− It does not arise from a rationale choice•− It does not arise from an engineering finalized analysis•− No one and nothing in the system says: I will do that because this will lead to a specific behavior of the system•− The individual in the system have no global perspective•− They are not aware of what’s globally happening•− They are not aware they are doing something intelligent

Page 7: Swarm Intelligence for Local Transit Revised 123

Multi-agent systems(MAS)The agents in a multi-agent system have several

important characteristics:• Autonomy: the agents are at least partially autonomous.• Local views: no agent has a full global view of the system,

or the system is too complex for an agent to make practical use of such knowledge.

• Decentralization: there is no designated controlling agent (or the system is effectively reduced to a monolithic system.

Typically multi-agent systems research refers to software agents. However, the agents in a multi-agent system could equally well be robots[6], humans or human teams. A multi-agent system may contain combined human-agent teams.

Page 8: Swarm Intelligence for Local Transit Revised 123

Naturally occurring algorithms• Ant colony optimization (ACO) is a class of optimization

algorithms modeled on the actions of an ant colony. ACO methods are useful in problems that need to find paths to goals. Artificial 'ants'—simulation agents—locate optimal solutions by moving through a parameter space representing all possible solutions.

• Particle swarm optimization (PSO) is a global optimization algorithm for dealing with problems in which a best solution can be represented as a point or surface in an n-dimensional space.

• Stochastic diffusion search (SDS) is an agent-based probabilistic global search and optimization technique best suited to problems where the objective function can be decomposed into multiple independent partial-functions. Each agent maintains a hypothesis which is iteratively tested by evaluating a randomly selected partial objective function parameterized by the agent's current hypothesis.

Page 9: Swarm Intelligence for Local Transit Revised 123

Naturally occurring algorithms(contd.)• Gravitational search algorithm (GSA) is

constructed based on the law of Gravity and the notion of mass interactions. The GSA algorithm uses the theory of Newtonian physics and its searcher agents are the collection of masses.

• Intelligent Water Drops algorithm (IWD) is a swarm-based nature-inspired optimization algorithm, which has been inspired from natural rivers and how they find almost optimal paths to their destination.These near optimal or optimal paths follow from actions and reactions occurring among the water drops and the water drops with their riverbeds.

Page 10: Swarm Intelligence for Local Transit Revised 123

Ant colony optimization

Ant colony optimization algorithms have been applied to many combinatorial optimization problems, ranging from quadratic assignment to fold protein or routing vehicles and a lot of derived methods have been adapted to dynamic problems in real variables, stochastic problems, multi-targets and parallel implementations.

Page 11: Swarm Intelligence for Local Transit Revised 123

The general algorithm is relatively simple and based on a set of ants, each making one of the possible round-trips along the cities. At each stage, the ant chooses to move from one city to another according to some rules:

1. It must visit each city exactly once;2. A distant city has less chance of being chosen (the visibility);3. The more intense the pheromone trail laid out on an edge

between two cities, the greater the probability that that edge will be chosen;

4. Having completed its journey, the ant deposits more pheromones on all edges it traversed, if the journey is short;

5. After each iteration, trails of pheromones evaporate.

Page 12: Swarm Intelligence for Local Transit Revised 123

Ant routing algorithm in AntColony Optimization

Ant agents are launched into a network, each

agent going from a source to a

destination node.

The ant agent maintains a list of visited nodes and

the time elapsed to arrive there and utilizes that

information to find a way backwards(like ants do

using pheromone).

At each node, the data package will use the digital pheromone

value as the transiting probability

for deciding data moving route.

Page 13: Swarm Intelligence for Local Transit Revised 123

Energy Balancing Routingin Sensor Network

An ad-hoc wireless network can largely

reduce energy consumption in

data transmission.

Virtual pheromone trail generate: Artificial forward ant agents are

launched regularly to destinations in the network. It maintains a list

of visited nodes and the time elapsed to arrive there and utilizes

same information to get backwards.

Virtual pheromone maintenance: At each sensor

node, the transiting probability is used for deciding data moving

route. The data package will reduce the node’s pheromone

value when it pass by the node.

Page 14: Swarm Intelligence for Local Transit Revised 123

Particle Swarm Optimization• Particle Swarm Optimization (PSO) is a population

based stochastic optimization technique inspired by social behavior of bird flocking.PSO applies the concept of social interaction to problem solving.

• In PSO, A group of agents, “particles”, are thrown into the search space. The particles communicate either directly or indirectly with one another for search directions (gradients).

• PSO is a simple but powerful search technique. It has been applied successfully to a wide variety of search and optimization problems.

Page 15: Swarm Intelligence for Local Transit Revised 123

Particle Swarm Optimization (PSO)in Dynamic Environment• The conventional PSO is used to discover the optimal solution in a static

environment. Conventional PSO has poor tracking characteristics when the optimal solution is moving.

• When the environment is dynamic, the task of the optimization is not only to acquire the extreme but also to track the extreme's trajectory as closely as possible.

• A human social adaptive based PSO is used to discover and track the optimal solution in a dynamic environment.

• Each particle evaluates the knowledge it received from it previous experience and from the neighbor’s experience.

• The outdated knowledge will be gradually forget by the particle and new knowledge will be learned.

Page 16: Swarm Intelligence for Local Transit Revised 123

Application of Ant System for vehicle routing problem

• Capacitated vehicle routing problem (CVRP)

• Multi-depot vehicle routing problem (MDVRP)

• Period vehicle routing problem (PVRP)

• Split delivery vehicle routing problem (SDVRP)

• Stochastic vehicle routing problem (SVRP)

• Vehicle routing problem with pick-up and delivery (VRPPD)

• Vehicle routing problem with time windows (VRPTW)

• Time Dependent Vehicle Routing Problem with Time Windows (TDVRPTW)

Page 17: Swarm Intelligence for Local Transit Revised 123

Vehicle routing problem with pick-up and delivery (VRPPD)

•Automation in pickup and delivery automation is gaining importance.

•But routing problems are faced when one or vehicles share same arena.

Solution Swarm intelligence

Page 18: Swarm Intelligence for Local Transit Revised 123

ARENA

Page 19: Swarm Intelligence for Local Transit Revised 123

ALGORITHM FOR SOLVING ABOVE PROBLEM

Search for object

along path

get nr. The

boundary

Place the object to the

reqd. position

Wait until other robot

comes in

Continue search along path If no boxes

found return in inside zone

and STOP

Return to the position from

where object was taken

Check if other

robot is in or out

If object detecte

d

yes

no

yes no

Page 20: Swarm Intelligence for Local Transit Revised 123

Applications of Ant ColonyOptimization

Traffic on telecommunications systems, he internet, roads, rail, and sea would all benefit from the reduction incongestion that efficient routing algorithms could provide.

Southwest airlines are actually putting the ant colony research to work, with impressive payback

British Telecom Network Southwest Airlines Cargo System

Page 21: Swarm Intelligence for Local Transit Revised 123

Swarm Robotics Surveillance systems(misc)

Surveillance systems are often needed in areas too hostile or dangerous for a direct human presence. One major problem is the control and coordination of multiple cooperating robots.

We have looked to the distributed control strategies found in nature in the form of social insects as an inspiration for new control schemes for the coordination and control of large-scale distributed robotic systems.

The research goal is to manipulate the interactions of multiple small, low-cost robots, with a limited range of local communication ability, to collaboratively search and engage tasks in an unknown large-scale hostile area.

Page 22: Swarm Intelligence for Local Transit Revised 123

Satellite

Maintenance

The Future?Medical

Interacting Chips

in Mundane

Objects

Cleaning Ship

Hulls

Pipe Inspection

Pest Eradication

Engine Maintenance

TelecommunicationsSelf-Assembling

Robots

Job Scheduling

Vehicle Routing Data Clustering

Distr

ibut

ed M

ail

Syst

ems

Optim

al

Resource

AllocationCombinatorial

Optimization

Page 23: Swarm Intelligence for Local Transit Revised 123

Conclusion• Swarm Intelligence is a scientific theory inspired from the

emergent behaviors of ants, birds and other social animals.• Swarm Intelligence proposes a new way of thinking the

solution of the non-linear complex problems.• The emergent property of swarm based MAS demonstrates

a fundamentally important principle that has been beneficial to nature.

• We are constrained by linear thinking: it is hard for us to understand how all the various parts of the system interact and add up to the whole.

• It is very important to use swarm intelligence to understand how large-scale emergent patterns and behaviors can result from the actions and interactions of the individual components of a system.

Page 24: Swarm Intelligence for Local Transit Revised 123

Thank you