Computers and Thought are the two categories that together define Artificial Intelligence as a discipline. It is generally accepted that work in Artificial Intelligence over the last thirty years has had a strong influence on aspects of computer architectures. In this paper we also make the converse claim; that the state of computer architecture has been a strong influence on our models of thought. The Von Neumann model of computation has lead Artificial Intelligence in particular directions. Intelligence in biological systems is completely different. Recent work in behavior-based Artificial Intelligence has produced new models of intelligence that are much closer in spirit to biological systems. The non-Von Neumann computational models they use share many characteristics with biological computation.

This paper surveys the developments of the last 20 years in the area of vision for mobile robot navigation. Two major components of the paper deal with indoor navigation and outdoor navigation. For each component, we have further subdivided our treatment of the subject on the basis of structured and unstructured environments. For indoor robots in structured environments, we have dealt separately with the cases of geometrical and topological models of space. For unstructured environments, we have discussed the cases of navigation using optical flows, using methods from the appearance-based paradigm, and by recognition of specific objects in the environment.

In this report, I discuss the use of vision to support concrete, everyday activity. I will argue that a variety of interesting tasks can be solved using simple and inexpensive vision systems. I will provide a number of working examples in the form of a state-of-the-art mobile robot, Polly, which uses vision to give primitive tours of the seventh floor of the MIT AI Laboratory. By current standards, the robot has a broad behavioral repertoire and is both simple and inexpensive (the complete robot was built for less than $20,000 using commercial board-level components). The approach I will use will be to treat the structure of the agent's activity--- its task and environment---as positive resources for the vision system designer. By performing a careful analysis of task and environment, the designer can determine a broad space of mechanisms which can perform the desired activity. My principal thesis is that for a broad range of activities, the space of applicable mechanisms will be broad...

This paper describes an `execution monitor' (EM); it is the key component of a control architecture designed to provide a car-like vehicle moving in a dynamic and partially known environment with motion autonomy. Specifically EM endows the vehicle with the reactive capabilities required in an uncertain environment. Its purpose is to generate the commands for the servo-systems of the vehicle so as to follow a given nominal trajectory while reacting in real-time to unexpected events. EM is designed as a fuzzy controller, i.e. a control system based upon fuzzy logic, thus permitting approximate reasoning and a `natural' description of the reactive behaviour of the vehicle. Besides EM differs from classical fuzzy controllers in two novel ways that improve it and allow for a partial automation of its design through the use of supervised learning. The characteristic features of EM along with the supervised learning process are presented in the paper. Keywords --- mobile-robot, control-archi...

The reactive component of a motion control architecture for a vehicle intended to move in a dynamic and partially known environment is presented in this paper. It is called the execution monitor (EM). Its purpose is to generate commands for the servo-systems of the vehicle so as to follow a given nominal trajectory while reacting in real-time to unexpected events. EM is designed as a fuzzy controller, i.e. a control system based upon fuzzy logic, whose main component is a set of linguistic rules that encode the reactive behaviour of the vehicle. EM differs from classical fuzzy controllers in two novel ways: first, it introduces a new defuzzification technique, the Barycentre of the Centres Of Area, that permits to better take into account the influence of each and every linguistic rule. Second, weighing coefficients are attached to the rules thus permitting a fine tuning of the vehicle's reactive behaviour. Furthermore it is shown how supervised learning, i.e. learning through samples,...

. This paper presents a control architecture endowing a car-like vehicle moving in a dynamic and partially known environment with autonomous motion capabilities. Like most recent control architectures for autonomous robot systems, it combines three functional components: a set of basic real-time skills, a reactive execution mechanism and a decision module. The main novelty of the architecture proposed lies in the introduction of a fourth component akin to a meta-level of skills: the sensor-based manoeuvres, i.e. general templates that encode high-level expert human knowledge and heuristics about how a specific motion task is to be performed. The concept of sensor-based manoeuvres permit to reduce the planning effort required to address a given motion task, thus improving the overall response-time of the system, while retaining the good properties of a skill-based architecture, i.e. robustness, flexibility and reactivity. The paper focuses on the trajectory planning function (which is a...

Computers and Thought are the two categories that together define Artificial Intelligence as a discipline. It is generally accepted that work in Artificial Intelligence over the last thirtyyears has had a strong influence on aspects of computer architectures. In this paper we also make the converse claim# that the state of computer architecture has been a strong influence on our models of thought. The Von Neumann model of computation has lead Artificial Intelligence in particular directions. Intelligence in biological systems is completely different. Recentwork in behavior-based Artificial Intelligence has produced new models of intelligence that are much closer in spirit to biological systems. The non-Von Neumann computational models they use share manycharacteristics with biological computation. Copyright c fl Massachusetts Institute of Technology, 1991 This report describes research done at the Artificial Intelligence Laboratory of the Massachusetts Institute of Technology. Support for this researchwas provided in part by the University Research Initiative under Office of Naval Research contract N00014--86--K--0685, in part bytheAdvanced Research Projects Agency under Office of Naval Researchcontract N00014-- 85--K--0124, in part by the Hughes Artificial Intelligence Center, in part by Siemens Corporation, and in part by Mazda Corporation. 1