Subsumption architecture

Subsumption means to incorporate new material into one's cognitive structures and Architecture means both the process and product of planning, designing and construction.

Introduction

Subsumption Architecture has a strong influence in the area of Autonomous robots. It is a reactive robot architecture heavily associated with behavior-based robotics. The term Subsumption Architecture was introduced by Rodney Brooks and colleagues in 1986. Subsumption has been widely influential in autonomous robotics and elsewhere in real-time AI.

Comparison of Traditional AI with subsumption architecture

Traditional Artificial Intelligence tends to rely on a centralized, top down, planning, execution and monitoring structure.

This Traditional approach to robotic control focuses mainly on the planning aspect of a robot’s behavioural cycle. The robot senses its environment and plans its next actions are based on these senses, then it takes appropriate action using available actuators. At each and every stage, the robot explicitly plans its next action from the the knowledge it has gathered about the environment so far. Essentially these robots are reflex agents, selecting actions from rule matches on the current perceptions from sensory input.

Since this approach using a top down design and sequential modules does not encourage a separation of concerns, and can introduce dependencies between functional layers, especially where feedback loops are used or output monitoring is required.

Subsumption architecture is a distributed, bottom up, reflexive approach to robot control.

This approach involves building robot control systems with increasing levels of competence. Each additional level potentially interacts with the inputs and outputs of existing one, previous levels to add higher levels of competency, leaving the lower levels intact, functional and operational within the overall system.

Overview

Subsumption architecture is a relatively new and simple approach to the control of robot systems. Traditional AI approach divides task into a number of major subsystems as follows: 1) Perception 2) Planning 3) Task Execution 4) motor control

Each of subsystems which are mentioned above are complex program and all have to work togetherly to operate robot perfectly. The Subsumption architecture approach to robot control is an alternative to the Traditional AI approach.

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 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 AI 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

. Advantages :

The main advantages of the methodology are: 1) The modularity 2) The emphasis on iterative development & testing of real-time systems in their target domain 3) 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.

. Disadvantages :

The main disadvantages of this model are: 1)The inability to have many layers, since the goals begin interfering with each other 2)The difficulty of designing action selection through highly distributed system of inhibition and suppression 3)The consequent rather low flexibility at runtime.

Applications

1) Industrial robotics.

See also

• Robotic paradigms
• Agent architecture
• Behavior based AI
• Behavior-based robotics
• Cognitive architecture
• Mibe architecture
• Emergent behavior
• Scruffies
• Situated
• Hierarchical control system

References

Key papers include:

• R. A. Brooks (1987). "Planning is just a way of avoiding figuring out what to do next", 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 (1991). "Intelligence Without Representation", Artificial Intelligence 47 (1991) 139-159. (Paper introduces concepts of Merkwelt and the Subsumption architecture.)
• [pdf]Mobile Robot Control:The Subsumption Architecture and occam-pi.
• [pdf]Cambrian Intelligence:The Early History of the New AI.

External links

• Subsumption Behaviors used for a Variety of Real World Tasks
• SB-MASE is a subsumption-based multi-agent simulator.
• Subsumption for the SR04 and jBot Robots , DPRG website
• Develop LeJOS programs step by step , Juan Antonio Breña Moral website