How can an artificial agent react to a situation after performing the correct amount of thinking? My Ph.D. dissertation (Zilberstein 1993)2 presents a theoretical framework and a programming paradigm that provide an answer to this question.

Moore's technique employs a conventional

In its early stages, the field of AI had as its main goal the invention of computer programs having the general problem-solving abilities of humans. Along the way, a major shift of emphasis developed from general-purpose programs toward performance programs, ones whose competence was highly specialized and limited to particular areas of expertise. In this article, I claim that AI is now at the beginning of another transition, one that will reinvigorate efforts to build programs of general, humanlike competence. These programs will use specialized performance programs as tools, much like humans do.

The possibility that the agents the authors make are a little unclear.

This design I thought I'd try something different. When I say built, I mean just servo couldn't turn fast enough to gather that: The students were given all the electronic enough data (the sonars can't be used while and mechanical components and, during the course, assembled and tested the circuit the servo is turning because they won't produce board (several smoky disasters here); built the reliable echoes). As a compromise, we chassis from bent aluminum sheet metal; used five sonars in the pattern shown in figure mounted motors, encoders, and wheels; and 3. The pivoting front sonar detects forward soldered a gazzillion cables to connect everything. I've had teaching a class.

We recently reported on the application of a machine-learning (ML) technique to automated flight control using a simulated F-16 combat plane (Michie and Camacho 1994). Subsequent tests of our data-induced flying model have broadly confirmed the reported results but have also identified a lack of robustness. We had underestimated the latter and now regard our report (Michie and Camacho 1994) as being, by omission, potentially misleading.

Boddy 1988) are employed wherever possible. 's software consists of a dozen different Sonar information is to and from the hardware components obtained at a rate of 1.3 hertz (Hz), and camera of the robot. On top of these, a fast images are processed at a rate of 0.7 Hz. obstacle-avoidance routine analyzes sonar's control software, as exhibited analyzing sonar information. It has been operated repeatedly and obstacles that block the path of the for durations as long as one hour in populated robot. 's control flow is monitored by an office environments without human integrated task planner and a central user intervention.

For example, why have Minton have a chapter on the modeling However, many application AIbased approaches garnered success and analysis of the effectiveness issues were not emphasized by the in these particular applications? How of this paradigm, and Miyashita technologists (such as how to present have ORbased approaches done in and Sycara describe a case-based bottleneck information to the user or these same applications? Why are AIbased approach to repair selection.

Georgia Tech's approach differed from other The contest required competing by the robots to collect trash; (3) cooperative robot entries to clean up a messy office behaviors provide for cooperation between strewn with trash. Wads of paper, Styrofoam robots; (4) temporal sequencing coordinates coffee cups, and soda cans were placed by transitions between distinct operating states judges throughout the contest arena along for each robot and achieves the desired goal with wastebaskets, where they hoped the state; (5) fast vision locates soda cans, wastebaskets, robots would deposit the trash. During competitive robot hardware and specifies behavioral states trials, each robot was to gather and throw and transitions between them; and (6) a realtime away as much trash as possible in 10 minutes. The task proved processing are outlined in the next section. The article closes trash in a wastebasket. Unfortunately, the with strategies used and lessons learned at the computational overhead was so great that competition. If a robot was The 10-pound robots were built using off-theshelf near an item of trash or a wastebasket, it components at a cost of approximately could signal its intent to pick up or throw $1700 each.

The third annual AAAI Robot Competition and Exhibition was held in 1994 during the Twelfth National Conference on Artificial Intelligence in Seattle, Washington. The competition was designed to showcase and compare the state of the art in autonomous indoor mobile robots. The competition featured Office Delivery and Office Cleanup events, which demanded competence in navigation, object recognition, and manipulation. The competition was organized into four parts: (1) a preliminary set of trials, (2) the competition finals, (3) a public robot exhibition, and (4) a forum to discuss technical issues in AI and robotics. Over 15 robots participated in the competition and exhibition. This article describes the rationale behind the events and the rules for the competition. It also presents the results of the competition and related events and provides suggestions for the direction of future exhibitions.