The world is its own best representation
Modelling intelligence requires a system to be directly interfaced with world through sensors and actuators. These layers of interaction approximate the sensorimotor dynamics of the human body and allow the world to act as its own representation.
This removes the necessity of using the inefficient global representations favoured by AI and has the advantages of:
- better response time, because no global representation has to be changed whenever the new environment changes;
- increased robustness, because the system is less likely to crash due to some unpredictable change in the world.
Rodney Brooks (1991).
Postulates of Subsumption Architecture
- A substantial architecture machine (STM) has sensors and actuators for interaction with the real world.
- A SAM is comprised of layers that is "activity producing subsystems" (p. 146). These layers interact with each other and with the world.
- Each layer is a complete functional unit; that is, it functions autonomously of other layers, without depending on any central control unit.
- Layers can be added gradually to SAMs, which can thus develop incrementally: "We must incrementally build up the capabilities of intelligent Systems, having complete systems at each step of the way and thus automatically ensure that the pieces in their interfaces are valid." (Page 140).
- Each layer enables a specific behaviour (e.g., obstacle avoidance, exploration, and union can retrieval, etc).
- Any given layer can "subsume" the action of attached layers in order to further its own goals, without completely wresting control from the attached layers.
- A SAM interacts with the ""that is, the dynamic world that humans act in; it does not act in a refined, abstracted, or limited "toy world". "At each step we should build complete intelligence systems that we let loose in the real world with real sensing and real action. Anything less provides a candidate with which we can delude ourselves." (p. 140).
From Brooks (1991), Subsumption architecture machine (SAM) is a term proposed by Horn's team.