Subsumption Architecture Methodological Assumptions
In this section, we consider the
subsumption architecture originally proposed
by
Brooks [1986].
The
subsumption (or 'Brooksian') architecture
is predicated on the synergy between sensation
and actuation in
lower animals such as insects. Brooks argues that instead
of building complex agents in simple worlds, we should follow the evolutionary
path and start building simple agents in the real,
complex and
unpredictable world.
From this argument, a number of key features of subsumption result:
- No explicit knowledge representation is used. Brooks
often refers to this as "The world is its own best model".
- Behavior is distributed
rather than centralized.
- Response to stimuli is
reflexive -- the perception-action sequence
is not modulated by cognitive deliberation.
- The agents are organized in a bottom-up fashion. Thus,
complex behaviors are fashioned from the combination of simpler, underlying ones.
- Individual agents are
inexpensive, allowing a domain to be populated by many
simple agents rather than a few complex ones. These simple agents individually consume
little resources (such as power) and are expendable, making the investment in each
agent minimal.
Several extensions (Mataric, 1992) have been proposed
to pure reactive subsumption systems. These extensions are known as behavior-based
architectures. Capabilities of behavior-based systems include
landmark detection
and map building, learning to walk, collective behaviors with homogeneous agents,
group learning with homogeneous agents, and heterogeneous agents.
Go to General Discussion of
Methodological Assumptions
Return to the top of this architecture.
Current Location: Subsumption-Methodological Assumptions