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.

In addition to process control, the forum plans to address issues related to evolving technologies, Eastman Kodak (Rochester, N.Y.), a most popular Internet navigator and FDA, EPA, and OSHA compliance, manufacturer of imaging-related products, front-end tools. CERN has chosen safety and environmental concerns, has developed an online neural Harlequin to continue development and application of industry network-based machine vision system and commercialization of its Web standards. KnowledgeBroker (Reno, Nev.), a This Windows-based inspection Ingersoll Milling Machines (Rockford, supplier of expert system-based help system automatically inspects and Ill.), a manufacturer of industrial desk support software, has signed a analyzes the fine-pitch solder paste products, has developed an expert system-based support contract with American physical quality. Following an initial neural network-based optical character schedules and reports on the activities rollout, KnowledgeBroker's HelpNet recognition (OCR) technology, has that need to be completed to successfully 800/900 Service will provide 24-hour signed an agreement to supply IBM install each customer's order. It live technical computer support for Ireland with OCR Readers for AN allows a customer to directly access shrink-wrapped software applications POST, Ireland's national postal service. The Federal Home Loan Mortgage ground data, control center Corp., better known as Freddie Mac BrainTech (Scottsdale, Ariz.), a developer hardware and software, has been of neural network and fuzzy logic-based Diego, Calif.) to use HNC's neural network-based Va.), a developer of acoustic systems La.), an oil refinery, has tested and Contel's subscribers will be able to The new software will allow traffic installed a neural network-based speak a natural stream of continuous controllers in the new $11 million application to control its atmospheric digits to place phone calls from Greater Houston Traffic and Emergency tower.

Sometimes a section will system shells, have made their way anew, and the reader must recall the introduce a list of points to be covered, into the marketplace.

DERVISH won the Office Delivery event of the 1994 Robot Competition and Exhibition, held as part of the Thirteenth National Conferennce on Artificial Intelligence. Although the contest required dervish to navigate in an artificial office environment, the official goal of the contest was to push the technology of robot navigation in real office buildings with minimal domain information. dervish navigates reliably using retractable assumptions that simplify the planning problem. In this article, we present a short description of Dervish's hardware and low-level motion modules. We then discuss this assumptive system in more detail.

The 1994 AAAI Robot-Building Laboratory (RBL-94) was held during the Twelfth National Conference on Artificial Intelligence. The primary goal of RBL-94 was to provide those with little or no robotics experience the opportunity to acquire practical experience in a few days. Thirty persons, with backgrounds ranging from university professors to practitioners from industry, participated in the three-part lab.

This paper presents a method for inducing logic programs from examples that learns a new class of concepts called first-order decision lists, defined as ordered lists of clauses each ending in a cut. The method, called FOIDL, is based on FOIL (Quinlan, 1990) but employs intensional background knowledge and avoids the need for explicit negative examples. It is particularly useful for problems that involve rules with specific exceptions, such as learning the past-tense of English verbs, a task widely studied in the context of the symbolic/connectionist debate. FOIDL is able to learn concise, accurate programs for this problem from significantly fewer examples than previous methods (both connectionist and symbolic).

There has been evidence that least-commitment planners can efficiently handle planning problems that involve difficult goal interactions. This evidence has led to the common belief that delayed-commitment is the "best" possible planning strategy. However, we recently found evidence that eager-commitment planners can handle a variety of planning problems more efficiently, in particular those with difficult operator choices. Resigned to the futility of trying to find a universally successful planning strategy, we devised a planner that can be used to study which domains and problems are best for which planning strategies. In this article we introduce this new planning algorithm, FLECS, which uses a FLExible Commitment Strategy with respect to plan-step orderings. It is able to use any strategy from delayed-commitment to eager-commitment. The combination of delayed and eager operator-ordering commitments allows FLECS to take advantage of the benefits of explicitly using a simulated execution state and reasoning about planning constraints. FLECS can vary its commitment strategy across different problems and domains, and also during the course of a single planning problem. FLECS represents a novel contribution to planning in that it explicitly provides the choice of which commitment strategy to use while planning. FLECS provides a framework to investigate the mapping from planning domains and problems to efficient planning strategies.

We study the process of multi-agent reinforcement learning in the context ofload balancing in a distributed system, without use of either centralcoordination or explicit communication. We first define a precise frameworkin which to study adaptive load balancing, important features of which are itsstochastic nature and the purely local information available to individualagents. Given this framework, we show illuminating results on the interplaybetween basic adaptive behavior parameters and their effect on systemefficiency. We then investigate the properties of adaptive load balancing inheterogeneous populations, and address the issue of exploration vs.exploitation in that context. Finally, we show that naive use ofcommunication may not improve, and might even harm system efficiency.