This editorial explains the benefits of preferences for AI systems and draws a picture of current AI research on preference handling. It thus provides an introduction to the topics covered by this special issue on preference handling. To act autonomously, the systems must choose among different actions and means of expression; to intelligently support humans' actions, they must understand and respond to the humans' choices. It is a natural assumption that agents who are acting in the world are experiencing the consequences of their actions and are not indifferent with respect to those experiences. An autonomous system such as a Mars rover can experience the consequences of moving along a path by measuring the energy consumption after the move, which will depend on the difficulty of the chosen path, and then judge whether the path was good or bad.

The map is composed of thousands of scene locations, and for each location there are tens of different images of varying quality to choose from. Constraints and preferences on map quality make it desirable to develop an automated solution to the map-generation problem. This article formulates a global map-generator problem as a constraint-optimization problem (GMG-COP) and describes an approach to solving it using local search. The article also describes the integration of a GMG solver into a graphical user interface for visualizing and comparing solutions, thus allowing for solutions to be generated with human participation and guidance. Data Center to produce a high-resolution mosaic map of the Earth.

"Solving Large-Scale Constraint Satisfaction and Scheduling Problems Using a Heuristic Repair Method," by Steve Minton, Mark Johnston, Andy Phillips, and Phil Laird clearly achieved both. It proved that local search and repair was applicable to a wide class of constraint-satisfaction problems and clearly explicated the theory behind that proof. The work epitomizes the guiding philosophy of that laboratory: AI research can simultaneously advance the state of the art and provide practical solutions to key problems faced by the Space Agency and its collaborators. Minton and colleagues developed a heuristic repair method, called "min-conflicts" for solving large-scale constraint-satisfaction problems (CSP), with a particular focus on massive scheduling tasks. Mark Johnston, an astronomer and computer scientist from the Space Telescope Science Institute at Johns Hopkins, served simultaneously as domain expert and codeveloper.

This problem is particularly pronounced for operations planners and controllers, who must be very highly knowledgeable and experienced with the business domain. This article is a case study of how one of the largest travel agencies in Hong Kong alleviated this problem by using AI to support decision making and problem solving so that its planners and controllers can work more effectively and efficiently to sustain business growth while maintaining consistent quality of service. AI is used in a mission-critical fleet management system (FMS) that supports the scheduling and management of a fleet of luxury limousines for business travelers. The AI problem was modeled as a constraint-satisfaction problem (CSP). The use of AI enabled the travel agency to sign up additional hotel partners, handle more orders, and expand its fleet with its existing team of planners and controllers.

In contrast to an explicit definition of each individual item, configurable products such as computers, financial service portfolios, and cars are repre sented in the form of a configuration knowledge base that de - scribes the properties of allowed instances. Although the knowledge representation used is different compared to nonconfi gurable products, the decision support requirements remain the same: users have to be supported in finding a solution that fits their wishes and needs. In this article we show how recommendation technologies can be applied for supporting the configuration of products. In addition to existing approaches we discuss relevant issues for future research. Similar to knowledge-based recommendation (Burke 2000) configuration is a process where users specify (and often adapt) their requirements and the configuration system provides feedback. Requirements specifications range from feature value definitions to textual queries specified on an informal level. Feedback is provided, for example, in terms of further questions that need to be answered, solutions (configurations), explanations of solutions, and proposals for relaxations of the user requirements in situations where no solution can be found. A major difference between configuration systems and recommender systems in general is the way in which product knowledge is represented. Configuration systems are operating on a configuration knowledge base (Stumptner 1997), which describes the properties of all allowed instances. In contrast to configuration systems, recommender systems are operating on the basis of an assortment of explicitly defined solution alternatives. The reason for using a configuration knowledge base is the large number of solution alternatives (possible configurations), which make an explicit representation infeasible. Although the used knowledge representations are different, the decision support goal is quite the same for both types of systems: users have to be proactively supported in finding a solution that fits their wishes and needs. Configuration systems often achieve this goal only partially since the amount and complexity of options presented by the configurator outstrip the capability of a user to identify an appropriate solution (configuration). Users are unable to find the features they would like to specify, they are unsure about their preferences regarding complex technical product properties, and they do not know how best to adapt their requirements in the case of inconsistencies (if no solution can be identified).

A set of challenges to researchers is presented that, we believe, must be met to ensure the practical applicability of parallel SAT solvers in the future. All these challenges are described informally but put into perspective with related research results, and a (subjective) grading of difficulty for each of them is provided. Parallelism is the wave of the future … and always will be. It conveys a general sentiment that the coming of parallel architectures would forever be delayed. This was indeed true at a time when clock-speed growth seemed always possible, allowing sequential code seamlessly to become faster.

This special issue of AI Magazine brings seven articles presenting extended versions of papers from IAAI 2013. These articles were selected for their description of AI technologies that are either in practical use or close to it. Five of the articles describe deployed application case studies. These articles present fielded AI applications that distinguish themselves for their innovative use of AI technology. One article describes an emerging application.

It deals with the practical application of constraint networks, using automated reasoning to overcome some of the blind spots in conventional iterative design. Parametric engineering design refers to routine-level design (Brown and Chandrasekaran 1985) in which the parameters and variables describing the design object are known, and the problem is one of finding a consistent set of parameter values that conform to specified requirements. It involves converting a well-established symbolic representation of an object, consisting of a set of parameters and variables, into a specific numeric representation. This conversion involves the attachment of numeric values to the parameters and the use of analysis programs to either verify the consistency of these values or eliminate inconsistent values. Conventional methods of parametric design rely on the iterative reuse of analysis programs to converge on a satisfactory solution.

In this article, we illustrate the motivations for distributed problem solving and provide an overview of two distributed problem-solving models, namely distributed constraint-satisfaction problems (DCSPs) and distributed constraint-optimization problems (DCOPs), and some of their algorithms. These agents are often assumed to be cooperative, that is, they are part of a team or they are self-interested but incentives or disincentives have been applied such that the individual agent rewards are aligned with the team reward. We illustrate the motivations for distributed problem solving with an example. Imagine a decentralized channel-allocation problem in a wireless local area network (WLAN), where each access point (agent) in the WLAN needs to allocate itself a channel to broadcast such that no two access points with overlapping broadcast regions (neighboring agents) are allocated the same channel to avoid interference. Figure 1 shows example mobile WLAN access points, where each access point is a Create robot fitted with a wireless CenGen radio card. Figure 2a shows an illustration of such a problem with three access points in a WLAN, where each oval ring represents the broadcast region of an access point. This problem can, in principle, be solved with a centralized approach by having each and every agent transmit all the relevant information, that is, the set of possible channels that the agent can allocate itself and its set of neighboring agents, to a centralized server.

Design problem solving is a complex activity involving a number of subtasks and a number of alternative methods potentially available for each subtask. The structure of tasks has been a key concern of recent research in task-oriented methodologies for knowledge-based systems (Chandrasekaran 1986; Clancey 1985; Steels 1990; McDermott 1988). One way to conduct a task analysis is to develop a task structure (Chandrasekaran 1989) that lays out the relation between a task, applicable methods for it, the knowledge requirements for the methods, and the subtasks set up by them. I propose a task structure for design by analyzing a general class of methods that I call proposecritique-modify methods. The task structure is constructed by identifying a range of methods for each task.