Subsumption architecture


Subsumption architecture

Subsumption architecture is a reactive robot architecture heavily associated with behavior-based robotics. The term was introduced by Rodney Brooks and colleagues in 1986cite journal
author = Brooks, R.
year = 1986
title = A robust layered control system for a mobile robot
journal = Robotics and Automation, IEEE Journal of [legacy, pre-1988]
volume = 2
issue = 1
pages = 14–23
url = http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1087032
accessdate = 2008-04-14
] cite conference
author = Brooks, R.
year = 1986
title = Asynchronous distributed control system for a mobile robot.
conference =
booktitle = SPIE Conference on Mobile Robots
pages = 77-84
publisher =
url = http://www.csa.com/partners/viewrecord.php?requester=gs&collection=TRD&recid=1481881CI
conferenceurl =
] [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.] . Subsumption has been widely influential in autonomous robotics and elsewhere in real-time AI.

Description

A subsumption architecture is a way of decomposing complicated intelligent behaviour into many "simple" behaviour modules, which are in turn organized into layers. Each layer implements a particular goal of the agent, and higher layers are increasingly more abstract. Each layer's goal subsumes that of the underlying layers, e.g. the decision to move forward by the eat-food layer takes into account the decision of the lowest obstacle-avoidance layer. As opposed to more traditional A.I. approaches subsumption architecture uses a bottom-up design.

For example, a robot's lowest layer could be "avoid an object", on top of it would be the layer "wander around", which in turn lies under "explore the world". Each of these horizontal layers access all of the sensor data and generate actions for the actuators — the main caveat is that separate tasks can suppress (or overrule) inputs or inhibit outputs. This way, the lowest layers can work like fast-adapting mechanisms (e.g. reflexes), while the higher layers work to achieve the overall goal. Feedback is given mainly through the environment.

Attributes of the architecture

The main advantages of the methodology are:
*the modularity,
*the emphasis on iterative development & testing of real-time systems in their target domain, and
*the emphasis on connecting limited, task-specific perception directly to the expressed actions that require it. These innovations allowed the development of the first robots capable of animal-like speeds. cite journal
author = Brooks, R.A.
year = 1990
title = Elephants Don't Play Chess
journal = Designing Autonomous Agents: Theory and Practice from Biology to Engineering and Back
url = http://books.google.com/books?hl=en&lr=&ie=UTF-8&id=cK-1pavJW98C&oi=fnd&pg=PA3-IA4&dq=Elephants+Don%27t+Play+Chess&ots=YOMgn9SDSp&sig=AJTzwrbA4mOCQ4qqsopVnkgpiX4
accessdate = 2008-04-06
]

Main disadvantages of this model are:
*the inability to have many layers, since the goals begin interfering with each other,
*the difficulty of designing action selection through highly distributed system of inhibition and suppression, and
*the consequent rather low flexibility at runtime.

References

Key papers include:
* R. A. Brooks (1987). [http://www.ece.osu.edu/~fasiha/Brooks_Planning.html "Planning is just a way of avoiding figuring out what to do next"] , Technical report, MIT Artificial Intelligence Laboratory.
* R. Brooks and A. 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 (1991). [http://citeseer.ist.psu.edu/brooks91intelligence.html "Intelligence Without Representation"] , Artificial Intelligence 47 (1991) 139-159. (Paper introduces concepts of Merkwelt and the Subsumption architecture.)

See also

* robotic paradigms
* agent architecture
* behavior based AI
* behavior-based robotics
* cognitive architecture
* emergent behavior
* scruffies
* situated
* hierarchical control system

External links

* [http://www.inl.gov/adaptiverobotics/autonomousbehaviors/index.shtml Subsumption Behaviors used for a Variety of Real World Tasks]
* [http://sourceforge.net/projects/sbmase/ SB-MASE] is a subsumption-based multi-agent simulator.
* [http://dprg.org/articles/2007-03a/ Subsumption for the SR04 and jBot Robots] , DPRG website
* [http://www.juanantonio.info/jab_cms.php?id=206 Develop LeJOS programs step by step] , Juan Antonio Breña Moral website


Wikimedia Foundation. 2010.

Look at other dictionaries:

  • Subsumption — may refer to:* A minor premise in symbolic logic (see syllogism) * The Liskov substitution principle in object oriented programming * Subsumption architecture in robotics * A subsumption relation in category theory, semantic networks and… …   Wikipedia

  • Mibe architecture — (Motivated Independent BEhavior) is a behavior based robot architecture developed at Artificial Intelligence and Robotics Lab of Politecnico di Milano by Fabio La Daga and Andrea Bonarini in 1998. MIBE architecture is based on the idea of animat… …   Wikipedia

  • Servo, subsumption, and symbolic architecture — The Servo, subsumption, and symbolic (SSS) architecture is a hybrid reactive/deliberative robot architecture developed by Jonathan H. Connell the IBM T.J. Watson Research Center. cite conference author = Connell, J.H. year = 1992 title = SSS: a… …   Wikipedia

  • Cognitive architecture — A cognitive architecture is a blueprint for intelligent agents. It proposes (artificial) computational processes that act like certain cognitive systems, most often, like a person, or acts intelligent under some definition. Cognitive… …   Wikipedia

  • Distributed architecture for mobile navigation (DAMN) — The Distributed architecture for mobile navigation (DAMN) is a reactive robot architecture developed by Julio K. Rosenblatt at Carnegie Mellon University.[1] DAMN consists of a collection of independently operating behaviors such as go to goal… …   Wikipedia

  • ATLANTIS architecture — The A Three Layer Architecture for Navigating Through Intricate Situations (ATLANTIS) is a hybrid reactive/deliberative robot architecture developed by Erann Gat at the Jet Propulsion Laboratory. cite conference author = Gat, E. year = 1992 title …   Wikipedia

  • Autonomous robot architecture (AuRA) — The Autonomous Robot Architecture (AuRA) is a hybrid deliberative/reactive robot architecture developed by Ronald C. Arkin at the Georgia Institute of Technology.cite journal author = Arkin, R.C. coauthors = Balch, T. year = 1997 title = AuRA:… …   Wikipedia

  • Three-layer architecture — The Three Layer Architecture is a hybrid reactive/deliberative robot architecture developed by R. James Firbycite book author = Firby, R.J. year = 1990 title = Adaptive Execution in Complex Dynamic Worlds publisher = isbn = ] that consists of… …   Wikipedia

  • Agent architecture — In computer science, agent architecture is a blueprint for software agents and intelligent control systems, depicting the arrangement of components. The architectures implemented by intelligent agents are referred to as cognitive… …   Wikipedia

  • Artificial intelligence — AI redirects here. For other uses, see Ai. For other uses, see Artificial intelligence (disambiguation). TOPIO, a humanoid robot, played table tennis at Tokyo International Robot Exhibition (IREX) 2009.[1] Artificial intelligence ( …   Wikipedia