This report summarises the papers presented in the expert assistants area at the First International Conference on Autonomous Agents. It describes the relationship between the expert assistants area and the other areas of the conference, and identifies the major research themes within this area.

Simultaneous localization and mapping (SLAM) is a well-known and fundamental topic for autonomous robot navigation. Existing solutions include the FastSLAM family-based approaches which are based on Rao–Blackwellized particle filter. The FastSLAM methods slow down greatly when the number of landmarks becomes large. Furthermore, the FastSLAM methods use a fixed number of particles, which may result in either not enough algorithms to find a solution in complex domains or too many particles and hence wasted computation for simple domains. These issues result in reduced performance of the FastSLAM algorithms, especially on embedded devices with limited computational capabilities, such as commonly used on mobile robots. To ease the computational burden, this paper proposes a modified version of FastSLAM called Adaptive Computation SLAM (ACSLAM), where particles are predicted only by odometry readings, and are updated only when an expected measurement has a maximum likelihood. As for the states of landmarks, they are also updated by the maximum likelihood. Furthermore, ACSLAM uses the effective sample size (ESS) to adapt the number of particles for the next generation. Experimental results demonstrated that the proposed ACSLAM performed 40% faster than FastSLAM 2.0 and also has higher accuracy.

Component-based development (CBD) has become an important emerging topic in the software engineering field. It promises long-sought-after benefits such as increased software reuse, reduced development time to market and, hence, reduced software production cost. Despite the huge potential, the lack of reasoning support and development environment of component modeling and verification may hinder its development. Methods and tools that can support component model analysis are highly appreciated by industry. Such a tool support should be fully automated as well as efficient. At the same time, the reasoning tool should scale up well as it may need to handle hundreds or even thousands of components that a modern software system may have. Furthermore, a distributed environment that can effectively manage and compose components is also desirable. In this paper, we present an approach to the modeling and verification of a newly proposed component model using Semantic Web languages and their reasoning tools. We use the Web Ontology Language and the Semantic Web Rule Language to precisely capture the inter-relationships and constraints among the entities in a component model. Semantic Web reasoning tools are deployed to perform automated analysis support of the component models. Moreover, we also proposed a service-oriented architecture (SOA)-based semantic web environment for CBD. The adoption of Semantic Web services and SOA make our component environment more reusable, scalable, dynamic and adaptive.

Default reasoning is concerned with making inferences in cases where the information at hand is incomplete. In such cases it is necessary to make plausible assumptions, which in default reasoning are based on default rules. This paper gives an introduction to the field. It discusses in depth one particular approach, default logic, including properties, semantics and computational models. It also gives an overview of other ideas and approaches.

WiMAX was proposed as the new wireless network standard in recent years. In the wide cover area of WiMAX environment, there are many nodes and interference. In order to obtain the efficiency, the avoidance to the interference is important. In this paper, we propose a two-tier cluster-based route scheduling mechanism on WiMAX Mesh mode. It achieves both fairness and efficiency inside and outside the cluster. The simulation result shows that our mechanism provides great improvement in average delay time and throughput than other research.

The emerging Grid is extending the scope of resources to mobile devices and sensors that are connected through loosely connected networks. Nowadays, the number of mobile device users is increasing dramatically and the mobile devices provide various capabilities such as location awareness that are not normally incorporated in fixed Grid resources. Nevertheless, mobile devices exhibit inferior characteristics such as poor performance, limited battery life, and unreliable communication, compared with fixed Grid resources. Especially, the intermittent disconnection from network owing to users’ movements adversely affects performance, and this characteristic makes it inefficient and troublesome to adopt the synchronous message delivery in mobile Grid. This paper presents a mobile Grid system architecture based on mobile agents that support the location management and the asynchronous message delivery in a multi-domain proxy environment. We propose a novel balanced scheduling algorithm that takes users’ mobility into account in scheduling. We analyzed users mobility patterns to quantitatively measure the resource availability, which is classified into three types: full availability, partial availability, and unavailability. We also propose an adaptive load-balancing technique by classifying mobile devices into nine groups depending on availability and by utilizing adaptability based on the multi-level feedback queue to handle the job type change. The experimental results show that our scheduling algorithm provides a superior performance in terms of execution times to the one without considering mobility and adaptive load-balancing.

Reinforcement learning (RL) algorithms are often used to compute agents capable of acting in environments without prior knowledge of the environment dynamics. However, these algorithms struggle to converge in environments with large branching factors and their large resulting state-spaces. In this work, we develop an approach to compress the number of entries in a Q-value table using a deep auto-encoder. We develop a set of techniques to mitigate the large branching factor problem. We present the application of such techniques in the scenario of a real-time strategy (RTS) game, where both state space and branching factor are a problem. We empirically evaluate an implementation of the technique to control agents in an RTS game scenario where classical RL fails and provide a number of possible avenues of further work on this problem.

There is little doubt that the strength and breadth of UK research into multi-agent systems continues to grow as we move into the new millennium. In the middle of an extremely cold December in 2000, the Third UK Workshop on Multi-Agent Systems (UKMAS 2001) was held at St Catherine's College, Oxford. This was the fifth such meeting in as many years, generously sponsored by EPSRC, FIPA (The Foundation for Intelligent Physical Agents) and Hewlett Packard.

Computational social choice is a new discipline currently emerging at the interface of social choice theory and computer science. It is concerned with the application of computational techniques to the study of social choice mechanisms, and with the integration of social choice paradigms into computing. The first international workshop specifically dedicated to this topic took place in December 2006 in Amsterdam, attracting a mix of computer scientists, people working in artificial intelligence and multiagent systems, economists, game and social choice theorists, logicians, mathematicians, philosophers, and psychologists as participants.

Hypothesis testing is uncommon in agent-based modeling and there are many reasons why (see Fagiolo et al. (2007) for a review). This is one of those uncommon studies: a combination of the new and old. First, a traditional neoclassical model of decision making is broadened by introducing agents who interact in an organization. The resulting computational model is analyzed using virtual experiments to consider how different organizational structures (different network topologies) affect the evolutionary path of an organization's corporate culture. These computational experiments establish testable hypotheses concerning structure, culture, and performance, and those hypotheses are tested empirically using data from an international sample of firms. In addition to learning something about organizational structure and innovation, the paper demonstrates how computational models can be used to frame empirical investigations and facilitate the interpretation of results in a traditional fashion.

Artificial intelligence (AI) planning solves the problem of generating a correct and efficient ordered set of instantiated activities, from a knowledge base of generic actions, which when executed will transform some initial state into some desirable end-state. There is a long tradition of work in AI for developing planners that make use of heuristics that are shown to improve their performance in many real world and artificial domains. The developers of planners have chosen between two extremes when defining those heuristics. The domain-independent planners use domain-independent heuristics, which exploit information only from the ‘syntactic’ structure of the problem space and of the search tree. Therefore, they do not need any ‘semantic’ information from a given domain in order to guide the search. From a knowledge engineering (KE) perspective, the planners that use this type of heuristics have the advantage that the users of this technology need only focus on defining the domain theory and not on defining how to make the planner efficient (how to obtain ‘good’ solutions with the minimal computational resources). However, the domain-dependent planners require users to manually represent knowledge not only about the domain theory, but also about how to make the planner efficient. This approach has the advantage of using either better domain-theory formulations or using domain knowledge for defining the heuristics, thus potentially making them more efficient. However, the efficiency of these domain-dependent planners strongly relies on the KE and planning expertise of the user. When the user is an expert on these two types of knowledge, domain-dependent planners clearly outperform domain-independent planners in terms of number of solved problems and quality of solutions. Machine-learning (ML) techniques applied to solve the planning problems have focused on providing middle-ground solutions as compared to the aforementioned two extremes. Here, the user first defines a domain theory, and then executes the ML techniques that automatically modify or generate new knowledge with respect to both the domain theory and the heuristics. In this paper, we present our work on building a tool, PLTOOL (planning and learning tool), to help users interact with a set of ML techniques and planners. The goal is to provide a KE framework for mixed-initiative generation of efficient and good planning knowledge.

We exploit the spreadsheet metaphor to make deductive problem-solving methods available to the vast population of spreadsheet end-users. In particular, we show how the function-based problem-solving capabilities of spreadsheets can be extended to include logical deductive methods in a way that is consistent with the existing spreadsheet ‘look and feel’. The foundation of our approach is the integration of a standard deductive logic system into a successful Commercial-Off-The-Shelf (COTS) spreadsheet. We have demonstrated this by designing and implementing an extension to Excel that manages the integration of Excel and a deductive logic engine based on the World Wide Web Consortium (W3C) standard ontology language OWL + SWRL.

Like the autonomic responses in the human body, autonomic computing systems recognize their own health problems and, where possible, respond to correct them. Failing that, external help is required. The purpose of this paper is to consider how autonomic systems might be structured to facilitate health monitoring. The approach uses a ‘pulse’ monitor for each autonomic element, which provides a reflex reaction facility and basic information on the current state (health) of that element. The pulse mechanism extends the NASA beacon monitor concept. The different ways that pulse information might be communicated and used are examined. The discussion is illustrated with a personal computing example.

This paper presents an empirical investigation of policy-based self-management techniques for parallel applications executing in loosely-coupled environments. The dynamic and heterogeneous nature of these environments is discussed and the special considerations for parallel applications are identified. An adaptive strategy for the run-time deployment of tasks of parallel applications is presented. The strategy is based on embedding numerous policies which are informed by contextual and environmental inputs. The policies govern various aspects of behaviour, enhancing flexibility so that the goals of efficiency and performance are achieved despite high levels of environmental variability. A prototype self-managing parallel application is used as a vehicle to explore the feasibility and benefits of the strategy. In particular, several aspects of stability are investigated. The implementation and behaviour of three policies are discussed and sample results examined.

Introduced as an interdisciplinary area that combines multi-agent systems, data mining and knowledge discovery, agent mining is currently in practice. To develop agent mining applications involves a combination of different approaches (model, architecture, technique and so on) from software agent and data mining (DM) areas. This paper presents an investigation of the approaches used in the agent mining systems by deeply analyzing 121 papers resulting from a systematic literature review. An ontology was defined to capitalize the knowledge collected from this study. The ontology is organized according to seven main facets: the problem addressed, the application domain, the agent-related and the mining-related elements, the models, processes and algorithms. This ontology is aimed at providing support to decisions about agent mining application design.

Expert systems technology has been around for a long time, becoming increasingly easy to use, inexpensive and reliable in recent years. It would seem to provide an ideal vehicle for the dissemination of expertise in developing countries, particularly in the field of medicine, which was the focus of much early work in diagnostic systems. Despite the apparent match of a real problem and a credible solution, however, remarkably few AI systems for medicine in developing countries have been researched, designed and implemented. This paper addresses why this might be the case, reviews some of the extant systems and explores some of the design issues. Particular emphasis is placed on the question of “Appropriate Technology”. Various criteria for Appropriate Technology are explored, and an optimal set used to guide principles of design. It is argued that medical AI systems can satisfy these criteria, provided that sufficient care is taken in their design for the country of application.

Statistical significance analysis, based on hypothesis tests, is a common approach for comparing classifiers. However, many studies oversimplify this analysis by simply checking the condition p-value < 0.05, ignoring important concepts such as the effect size and the statistical power of the test. This problem is so worrying that the American Statistical Association has taken a strong stand on the subject, noting that although the p-value is a useful statistical measure, it has been abusively used and misinterpreted. This work highlights problems caused by the misuse of hypothesis tests and shows how the effect size and the power of the test can provide important information for better decision-making. To investigate these issues, we perform empirical studies with different classifiers and 50 datasets, using the Student’s t-test and the Wilcoxon test to compare classifiers. The results show that an isolated p-value analysis can lead to wrong conclusions and that the evaluation of the effect size and the power of the test contributes to a more principled decision-making.