Information Technology Reference
In-Depth Information
Chapter 11
AUTOPÍA Program for Intelligent
Control of Vehicles
Teresa de Pedro
11.1 Introduction
Since its beginning the guideline of the AUTOPÍA program has been to apply
the robot control techniques to controling serial road vehicles. Among all them
AUTOPÍA has taken possession of the artificial intelligent techniques, namely a
combination of agent theory, fuzzy logic and evolutionary and swarm algorithms.
These techniques provide power, flexibility and generality to the found solutions as
to the individual control as to the cooperative control of vehicles and even to the
traffic control. In effect, the agent theory allows to create a modular architecture,
attaining the level of detail that requires the application. The fuzzy logic allows
modeling the behavior of the planning, cooperation and decision agents according
to the human way of doing, the evolutionary algorithms allow to adjust the agent
behavior to optimize the operation or cost criteria and the swarm algorithms allow
modeling the emergent behavior of a great number of individual agents, in our case
the traffic flow, in particular the urban traffic flow. To support these statements we
are going to consider the analogies and differences that, from the conceptual point
of view, there are between a real application—an automatic pilot for a car—and a
virtual one—a cybernetic rider.
In a first approach we can consider that the environments are similar in the two
cases, nevertheless the human actions and the devices to ride a horse or to pilot a vehi-
cle are different. A rider guides the horse by controling the stirrup, the spurs, the reins
the bridle, etc. while a driver guides the vehicle controling the accelerator, the brake
and the steering-wheel; thus the action agents will be different for each application.
According to the agent theory we could build similar architectures to implement
Search WWH ::
Custom Search