Page 164 - Introduction to AI Robotics

147
4.5 Evaluation of Reactive Architectures
haviors. The coordinated control program is not specified; the designer
can use logic, finite state machines, whatever is deemed appropriate. Se-
quencing is usually controlled by perceived cues or affordances in the en-
vironment, which are releasers.

Although all behaviors are treated equally, behaviors may make varying
contributions to the overall action of the robot. A behavior can change
the gains on another behavior, thereby reducing or increasing the magni-
tude of its output. This means that behaviors can inhibit or excite other
behaviors, although this is rarely used in practice.

Perception is usually handled by direct perception or affordances.

Perception can be shared by multiple behaviors. A priori knowledge can
be supplied to the perceptual schemas, to emulate a specialized sensor
being more receptive to events such as hall boundary spacing.

4.5 Evaluation of Reactive Architectures

As seen by the follow-corridor example, the two styles of architectures are
very similar in philosophy and the types of results that they can achieve.
Essentially, they are equivalent.
In terms of support for modularity, both decompose the actions and per-
ceptions needed to perform a task into behaviors, although there is some dis-
agreement over the level of abstraction of a behavior. Subsumption seems to
favor a composition suited for a hardware implementation, while potential
fields methods have nice properties for a software-oriented system.
The niche targetability is also high for both, assuming that the task can
be performed by reflexive behaviors. Indeed, the use of direct perception
emphasizes that reactive robots are truly constructed to fill a niche.
The issue of whether these architectures show an ease of portability to
other domains is more open. Reactive systems are limited to applications
which can be accomplished with reflexive behaviors. They cannot be trans-
ferred to domains where the robot needs to do planning, reasoning about
resource allocation, etc. (this led to the Hybrid Paradigm to be described in
Ch. 7). In practice, very few of the subsumption levels can be ported to new
applications of navigating in an environment without some changes. The
different applications create layers which need to subsume the lower layers
differently. The potential fields methodology performs a bit better in that the