Subsumption architecture
Subsumption architecture is a reactive robotic architecture heavily associated with behavior-based
robotics which was very popular in the 1980s and 90s. The term was introduced by Rodney Brooks and
colleagues in 1986.[1][2][3] Subsumption has been widely influential in autonomous robotics and
elsewhere in real-time AI.
Overview
Subsumption architecture is a control architecture that was proposed in opposition to traditional symbolic
AI. Instead of guiding behavior by symbolic mental representations of the world, subsumption
architecture couples sensory information to action selection in an intimate and bottom-up fashion.[4]: 130
It does this by decomposing the complete behavior into sub-behaviors. These sub-behaviors are organized
into a hierarchy of layers. Each layer implements a particular level of behavioral competence, and higher
levels are able to subsume lower levels (= integrate/combine lower levels to a more comprehensive
whole) in order to create viable behavior. For example, a robot's lowest layer could be "avoid an object".
The second layer would be "wander around", which runs beneath the third layer "explore the world".
Because a robot must have the ability to "avoid objects" in order to "wander around" effectively, the
subsumption architecture creates a system in which the higher layers utilize the lower-level competencies.
The layers, which all receive sensor-information, work in parallel and generate outputs. These outputs can
be commands to actuators, or signals that suppress or inhibit other layers.[5]: 8–12, 15–16
Goal
Subsumption architecture attacks the problem of intelligence from a significantly different perspective
than traditional AI. Disappointed with the performance of Shakey the robot and similar conscious mind
representation-inspired projects, Rodney Brooks started creating robots based on a different notion of
intelligence, resembling unconscious mind processes. Instead of modelling aspects of human intelligence
via symbol manipulation, this approach is aimed at real-time interaction and viable responses to a
dynamic lab or office environment.[4]: 130–131
The goal was informed by four key ideas:
Situatedness – A major idea of situated AI is that a robot should be able to react to its
environment within a human-like time-frame. Brooks argues that situated mobile robot
should not represent the world via an internal set of symbols and then act on this model.
Instead, he claims that "the world is its own best model", which means that proper
perception-to-action setups can be used to directly interact with the world as opposed to
modelling it. Yet, each module/behavior still models the world, but on a very low level, close
to the sensorimotor signals. These simple models necessarily use hardcoded assumptions
about the world encoded in the algorithms themselves, but avoid the use of memory to
predict the world's behavior, instead relying on direct sensorial feedback as much as
possible.
Embodiment – Brooks argues building an embodied agent accomplishes two things. The
first is that it forces the designer to test and create an integrated physical control system, not
theoretic models or simulated robots that might not work in the physical world. The second
is that it can solve the symbol grounding problem, a philosophical issue many traditional AIs
encounter, by directly coupling sense-data to meaningful actions. "The world grounds
regress," and the internal relation of the behavioral layers are directly grounded in the world
the robot perceives.
Intelligence – Looking at evolutionary progress, Brooks argues that developing perceptual
and mobility skills are a necessary foundation for human-like intelligence. Also, by rejecting
top-down representations as a viable starting point for AI, it seems that "intelligence is
determined by the dynamics of interaction with the world."
Emergence – Conventionally, individual modules are not considered intelligent by
themselves. It is the interaction of such modules, evaluated by observing the agent and its
environment, that is usually deemed intelligent (or not). "Intelligence," therefore, "is in the
eye of the observer."[5]: 165–170
The ideas outlined above are still a part of an ongoing debate regarding the nature of intelligence and how
the progress of robotics and AI should be fostered.
Layers and augmented finite-state machines
Each layer is made up by a set of processors that are augmented finite-state machines (AFSM), the
augmentation being added instance variables to hold programmable data-structures. A layer is a module
and is responsible for a single behavioral goal, such as "wander around." There is no central control
within or between these behavioral modules. All AFSMs continuously and asynchronously receive input
from the relevant sensors and send output to actuators (or other AFSMs). Input signals that are not read
by the time a new one is delivered end up getting discarded. These discarded signals are common, and is
useful for performance because it allows the system to work in real time by dealing with the most
immediate information.
Because there is no central control, AFSMs communicate with each other via inhibition and suppression
signals. Inhibition signals block signals from reaching actuators or AFSMs, and suppression signals
blocks or replaces the inputs to layers or their AFSMs. This system of AFSM communication is how
higher layers subsume lower ones (see figure 1), as well as how the architecture deals with priority and
action selection arbitration in general.[5]: 12–16
The development of layers follows an intuitive progression. First, the lowest layer is created, tested, and
debugged. Once that lowest level is running, one creates and attaches the second layer with the proper
suppression and inhibition connections to the first layer. After testing and debugging the combined
behavior, this process can be repeated for (theoretically) any number of behavioral modules.[5]: 16–20
Robots
The following is a small list of robots that utilize the subsumption architecture.
Allen (robot)
Herbert, a soda can collecting robot (see external links for a video)
Genghis, a robust hexapodal walker (see external links for a video)
The above are described in detail along with other robots in
Elephants Don't Play Chess.[6]
Strengths and weaknesses
The main advantages of the architecture are:
Figure 1: Abstract representation of
subsumption architecture, with the
the emphasis on iterative development and testing of
higher level layers subsuming the
real-time systems in their target domain;
roles of lower level layers when the
the emphasis on connecting limited, task-specific sensory information determines
perception directly to the expressed actions that require
it.[5]: 11
it; and
the emphasis on distributive and parallel control, thereby
integrating the perception, control, and action systems in a manner similar to
animals.[5]: 172–173 [6]
The main disadvantages of the architecture are:
the difficulty of designing adaptable action selection through highly distributed system of
inhibition and suppression;[4]: 139–140 and
the lack of large memory and symbolic representation, which seems to restrict the
architecture from understanding language;
When subsumption architecture was developed, the novel setup and approach of subsumption
architecture allowed it to be successful in many important domains where traditional AI had failed,
namely real-time interaction with a dynamic environment. The lack of large memory storage, symbolic
representations, and central control, however, places it at a disadvantage at learning complex actions, in-
depth mapping, and understanding language.
See also
Agent architecture
Cognitive architecture
Emergent behavior
Hierarchical control system
Mibe architecture
Robotic paradigms
Scruffies
Notes
1. Brooks, R. (1986). "A robust layered control system for a mobile robot". IEEE Journal of
Robotics and Automation. 2 (1): 14–23. doi:10.1109/JRA.1986.1087032 (https://doi.org/10.1
109%2FJRA.1986.1087032). hdl:1721.1/6432 (https://hdl.handle.net/1721.1%2F6432).
S2CID 10542804 (https://api.semanticscholar.org/CorpusID:10542804).
2. Brooks, R. (1986). "Asynchronous distributed control system for a mobile robot." (http://ww
w.csa.com/partners/viewrecord.php?requester=gs&collection=TRD&recid=1481881CI).
SPIE Conference on Mobile Robots. pp. 77–84.
3. Brooks, R. A., "A Robust Programming Scheme for a Mobile Robot", Proceedings of NATO
Advanced Research Workshop on Languages for Sensor-Based Control in Robotics,
Castelvecchio Pascoli, Italy, September 1986.
4. Arkin, Ronald (1998). Behavior-Based Robotics. Cambridge, Massachusetts: The MIT
Press. ISBN 978-0-262-01165-5.
5. Brooks, Rodney (1999). Cambrian Intelligence: The Early History of the New AI. Cambridge,
Massachusetts: The MIT Press. ISBN 978-0-262-02468-6.
6. Brooks, R.A. (1990). Elephants Don't Play Chess (https://books.google.com/books?id=cK-1
pavJW98C&dq=Elephants+Don%27t+Play+Chess&pg=PA3-IA4). MIT Press. ISBN 978-0-
262-63135-8. Retrieved 2013-11-23. {{cite book}}: |journal= ignored (help)
References
Key papers include:
R. A. Brooks (1986), "A Robust Layer Control System for a Mobile Robot (https://apps.dtic.m
il/dtic/tr/fulltext/u2/a160833.pdf)", IEEE Journal of Robotics and Automation RA-2, 14-23.
R. A. Brooks (1987), "Planning is just a way of avoiding figuring out what to do next" (http://p
eople.csail.mit.edu/brooks/papers/Planning%20is%20Just.pdf), Technical report, MIT
Artificial Intelligence Laboratory.
R. Brooks and A. Flynn (Anita M. Flynn) (1989), "Fast, cheap, and out of control: A robot
invasion of the solar system," J. Brit. Interplanetary Soc., vol. 42, no. 10, pp. 478–485, 1989.
(The paper later gave rise to the title of the film Fast, Cheap and Out of Control, and the
paper's concepts arguably have been seen in practice in the 1997 Mars Pathfinder and then
2004 Mars Exploration Rover Mission.)
R. A. Brooks (1991b), "Intelligence Without Reason (https://dspace.mit.edu/bitstream/handl
e/1721.1/6569/AIM-1293.pdf)", in Proceedings of the 1991 International Joint Conference on
Artificial Intelligence, pp. 569–595.
R. A Brooks (1991c), "Intelligence Without Representation" (http://citeseer.ist.psu.edu/brook
s91intelligence.html), Artificial Intelligence 47 (1991) 139-159. (Paper introduces concepts of
Merkwelt and the Subsumption architecture.)
External links
SB-MASE (http://sourceforge.net/projects/sbmase/) is a subsumption-based multi-agent
simulator.
Subsumption for the SR04 and jBot Robots (http://dprg.org/articles/2007-03a/), DPRG
website
Develop LeJOS programs step by step (http://www.juanantonio.info/jab_cms.php?id=206),
Juan Antonio Breña Moral website
Video of Herbert, the soda can collecting robot (https://www.youtube.com/watch?v=YtNKuwi
VYm0), YouTube.
Video of Genghis, a robust hexapodal walker (https://www.youtube.com/watch?v=K2xUHYF
cYKI), YouTube.
Retrieved from "https://en.wikipedia.org/w/index.php?title=Subsumption_architecture&oldid=1168864924"
