Autonomous Robot Architecture (AuRA)

Autonomous Robot Architecture (AuRA)
AUTONOMOUS ROBOT 
ARCHITECTURE
(AURA)

Autonomous Robot Architecture (AuRA) is the oldest of the

 Hybrids. It was

actually designed and implemented by Arkin at the same time Brooks was
beginning to publish his work with subsumption. AuRA is based on schema
theory, and consists of five subsystems, equivalent to object-oriented classes.
Two of the subsystems comprise the deliberative portion: the Planner, and
the Cartographer. The Planner is responsible for mission and task planning.
It is subdivided into three components, equivalent to the Nested Hierarchical
Controller93 discussed in Ch. 2. The Cartographer encapsulates all the map
making and reading functions needed for navigation. The Cartographer can
also be given an a priori map. For example, a human operator might load in
a map file for the Cartographer to use. The three components of the Planner
would interact with the Cartographer through methods to obtain a path to
follow, broken down into subsegments.
The Planner subsystem is divided into theMission Planner, Navigator, and
Pilot. The Mission Planner serves as the interface with the human, and the
current implementation of AuRA has one of the most extensive and user
friendly robot interfaces available. The Navigator works with the Cartographer
to compute a path for the robot and break it into subtasks (go over the
mountain to the water tower, follow the road along the ridge to the camp).
The Pilot takes the first subtask (go over the mountain to the water tower)
and gets relevant information (terrain, foliage types, what the water tower
looks like) to generate behaviors. The Pilot portion of the Planning subsystem
interacts with the Motor Schema Manager in the Motor subsystem, giv-

which form the behavior schema. The schemas themselves can consist of assemblages
of primitive schemas, coordinated by finite state machines. Schemas
can share information, if necessary, through links established by the
Motor Schema Manager. Behaviors are not restricted to being purely reflexive;
behavior specific knowledge, representations, and memory is permitted
within the schemas. The motor schemas, however, are restricted to potential
fields.
The fifth subsystem, Homeostatic Control, falls into a gray area between
deliberation and reaction. The purpose of Homeostatic control is to modify
the relationship between behaviors by changing the gains as a function of the
“health” of the robot or other constraints. As an example, consider a planetary
rover operating on a rocky planet. The robot is tasked to physically
remove rock samples from various locations around the planet and deliver
them to a return vehicle. The return vehicle has a fixed launch date; it will
blast off, returning to Earth on a set day and time no matter what. Now, the
rover may be provided with default gains on its behaviors which produce
a conservative behavior. It may stay two meters away from each obstacle,
giving itself a wide margin of error. At the beginning of the mission, such a
conservative overall behavior appears reasonable. Now consider what happens
towards the time when the return vehicle is set to launch. If the robot is
near the return vehicle, it should be willing to shave corners and reduce the
margin by which it avoids obstacles in order to ensure delivery. The robot
should be willing to perform the equivalent of sacrificing its own existence
for the sake of the mission.
The issue becomes how to do homeostatic. Many aspects of AuRA are
motivated by biology, and homeostatic control is no exception. Rather than
put a module in the deliberative portion to explicitly reason about how to
change the overall behavior of the robot, biology suggests that animals subconsciously
modify their behaviors all the time in response to internal needs.
For example, an animal who needs food becomes increasingly focused on
finding food. Human behavior changes in response to insulin. Fortunately,
changing the emergent behavior is straightforward in a potential fields representation
of behaviors, since the output vector produced by each behavior
can be scaled by a gain term. Returning to the case of the planetary rover
rushing to make the last delivery, the gain on the move-to-goal behavior attracting
the rover to the return vehicle should start going up, while the gain
on the avoid-obstacle behavior should start going down as a function of time
to launch.