Biomedical Engineering Reference
In-Depth Information
INTRODUCTION
control layer giving appropriate set points to the
lower level controllers, in a clear hierarchical
structured control (Acosta et. al, 2001). Conse-
quently, every control layer could be approached
with many different and heterogeneous tech-
niques. Nevertheless, to better focus within the
scope of this topic, current technology on mobile
robot path generation with AI and CI techniques
will be analyzed in more detail in next sections.
The main goal of this chapter is to describe the
authors' experiences in developing trajectory
generation systems for autonomous robots, us-
ing artificial intelligence (AI) and computational
intelligence (CI) methodologies. During this
engineering work, some questions have arisen
that motivated the exploration of new techniques
like ER and the behaviour coordination with ar-
tificial immune systems. This maturing process
as well as new questions and hypotheses for the
suitability of each technique are presented in the
following paragraphs.
In order to provide paths to an autonomous
mobile robot, being it terrestrial, aerial or aquatic,
there are some basic building blocks that must be
necessary present. One essential feature needed
consists on on-board sensory systems to have
perception of the world and the robot's presence
in the environment. This will be called the navi-
gation system. Another necessary feature is the
low-level trajectory generation from the next target
position and the robot's current position, referred
as the guidance system. Finally, the lowest level
feedback loops allowing the robot to describe a
trajectory as close as possible to the proposed
path (Fossen, 2002), (Meystel, 1991), named the
control system.
A top hierarchy module is responsible of gen-
erating the next target positions for the robot, and
then, the whole trajectory or path. This module is
called the mission planner and varies according to
the mobile robot application domain. The mission
plan can be given beforehand (static planning) or
it can be changed on-line as the robot movement
progresses in the real world (dynamic planning
or replanning). Mission replanning is the robot's
response to the changing environment (obstacle
avoidance, changes in mission objectives priori-
ties, and others).
The navigation, the guidance and the mission
planner systems providing trajectories for the
mobile robot, may be considered as a supervisory
bACkGROUND
The guidance system is usually designed to navi-
gate joining two points, routing over intermediate
points between actual robot position and the target
position. These points, called waypoints, vary in
number from one approach to another, but in every
case, they represent intermediate goals to fulfil
when going towards the final one. Even further,
a complete mission is split in a great number of
intermediate trajectories; each conformed by
more than one waypoints. The navigation system
comprises the data fusion necessary to locate
precisely in 3D the robot rigid body (considering
it as holonomic or non-holonomic) and the target
position. The components within the navigation
system can be geostationary positional system
(GPS), an inertial navigations system (INS), a
compass, a depth sensor, sonars, lasers, video
images, and others. Thus, the navigation system
provides the mission planner system, the guidance
system and the control system with accurate data
to achieve their objectives. Although this problem
is faced with several techniques, AI is employed
to organize the information in such a way that
sensor readings are transformed into a kind of
perception. Several approaches use artificial
vision or pattern recognition with sonars, also
considered as machine intelligence (Antonelli,
Chiaverini, Finotello & Schiavon, 2001), (Conte,
Zanoli, Perdon & Radicioni 1994), (Borenstein &
Koren, 1991), (Warren, 1990), (Yoerger, Bradley,
Walden, Singh & Bachmayer, 1996), (Hyland &
Search WWH ::
Custom Search