Rodney A. Brooks

A new architecture for controlling mobile robots is described. Layers of control system are built to let the robot operate at increasing levels of competence. Layers are made up of asynchronous modules that communicate over low-bandwidth channels. Each module is an instance of a fairly simple computational machine. Higher-level layers can subsume the roles of lower levels by suppressing their outputs. However, lower levels continue to function as higher levels are added. The result is a robust and flexible robot control system. The system has been used to control a mobile robot wandering around unconstrained laboratory areas and computer machine rooms. Eventually it is intended to control a robot that wanders the office areas of our laboratory, building maps of its surroundings using an onboard arm to perform simple tasks.

The new approaches that have been developed recently for artificial intelligence (AI) arose from work with mobile robots. This chapter outlines the context within which this work arose and discusses some key realizations made by the researchers involved. It traces the development of the foundational ideas for AI, and how they were intimately linked to the technology available for computation. The chapter provides a brief overview of developments in the understanding of biological intelligence. It covers material from ethology, psychology, and neuroscience. The chapter also introduces the two cornerstones to the new approach to AI, situatedness and embodiment, and discusses both intelligence and emergence in these contexts. It outlines some details of the approach of group at Massachusetts Institute of Technology to building complete situated, embodied, artificially intelligent robots. This approach shares more heritage with biological systems than with what is usually called AI.