Prof M S Prasad
Invited Talk
Centre for Artificial Intelligence & Robotics
DRDO , Banglore 2016
Swarms, and how they might inspire us
There are some interesting things that come to mind when we
think of swarms (flocks, schools, etc …):
• A swarm sometimes seems to behave as if it is an individual organism.
Ants or wasps on a hunt for food, or on the attack, behave as if with a single
mind, co-ordinating different actions with different parts of the swarm.
Behavioral Algorithm
In order to achieve full autonomous self
stabilizing automata we needed a strong
stable and efficient algorithm which
will able a UAV to move around in solo
and in group mode.
Reynolds found that he had to be careful about how the vectors from
the three rules get combined. It is not ideal to simply add them.
Opposing “shouts” from two rules may cancel out, leading to
the third winning – in what scenarios might this be a problem?
goal (0,0);
neighbours getNeighbours(boid);
for each nBoid in neighbours
do
goal --- goal + positionOf(nBoid);
end
goal ---- goal / neighbours.size();
Steer forward(goal, boid);
% cohesion
Reynolds second rule: Separation.
goal (0,0);
neighbours getNeighbours(boid);
foreach nBoid in neighbours
do
goal --- goal + positionOf(boid) - positionOf(nBoid);
end
goal --- goal / neighbours.size();
Steer forward(goal, boid);
Computational Power
–Computational power advancing –can now support micro-
simulations
Agent definitions
• “Most often, when people use the term ‘agent’
they refer to an entity that functions continuously
and autonomously in an environment in which
other processes take place and other agents exist.”
(Shoham, 1993)
• “An agent is an entity that senses its environment
and acts upon it” (Russell, 1997)
•What is an agent?
•–A discrete entity with its own goals and behaviors
•–Autonomous, with a capability to adapt and modify its behaviors
• Assumptions
– Some key aspect of behaviors can be described.
– Mechanisms by which agents interact can be described.
– Complex social processes and a system can be built “from the
bottom up.”
Agents are diverse and heterogeneous
• Goals, rationality
• Reasoning, decision making cognitive
• Learning/adaptation
• Interaction with other agents - social dimension
Other basis for intelligence?
62
No central authority or controller exists for:
–How the system operates
–How the system is modeled
–How the system/model moves from state
to state
“Optimization”can be done for the
system as a whole
Multi-agent systems
Many entities (agents) in a common
environment
Environment
69
Communication
communication protocol
communication language
- negotiation to reach agreement
- ontology
Organizational structures
centralized vs decentralized
hierarchical/ markets
"cognitive agent" approach
70
SWARM INTELLIGENCE
Swarm intelligence (SI) is the collective behavior of
decentralized, self-organized systems, natural or artificial. The
concept is employed in work on artificial intelligence. The
expression was introduced by Gerardo Beni and Jing
SI systems consist typically of a population of simple agents or
boids interacting locally with one another and with their
environment. The inspiration often comes from nature, especially
biological systems.