Coordination infrastructures play a central role in the engineering of multiagent systems. Since the advent of agent technology, research on coordination infrastructures has produced a significant number of infrastructures with varying features. In this paper, we review the the state-of-the-art coordination infrastructures with the purpose of identifying open research challenges that next generation coordination infrastructures should address. Our analysis concludes that next generation coordination infrastructures must address a number of challenges: (i) to become socially aware, by facilitating human interaction within a MAS; (ii) to assist agents in their decision making by providing decision support that helps them reduce the scope of reasoning and facilitates the achievement of their goals; and (iii) to increase openness to support on-line, fully decentralised design and execution. Furthermore, we identify some promising approaches in the literature, together with the research issues worth investigating, to cope with such challenges.

Designing hierarchical reinforcement learning algorithms that exhibit safe behaviour is not only vital for practical applications but also facilitates a better understanding of an agent’s decisions. We tackle this problem in the options framework (Sutton, Precup & Singh, 1999), a particular way to specify temporally abstract actions which allow an agent to use sub-policies with start and end conditions. We consider a behaviour as safe that avoids regions of state space with high uncertainty in the outcomes of actions. We propose an optimization objective that learns safe options by encouraging the agent to visit states with higher behavioural consistency. The proposed objective results in a trade-off between maximizing the standard expected return and minimizing the effect of model uncertainty in the return. We propose a policy gradient algorithm to optimize the constrained objective function. We examine the quantitative and qualitative behaviours of the proposed approach in a tabular grid world, continuous-state puddle world, and three games from the Arcade Learning Environment: Ms. Pacman, Amidar, and Q*Bert. Our approach achieves a reduction in the variance of return, boosts performance in environments with intrinsic variability in the reward structure, and compares favourably both with primitive actions and with risk-neutral options.

We analyze the problem of modeling and developing multiagent systems (MASs) from the organizational theory point of view. In particular, we focus on the critical issue of adapting MASs organizations whenever changes in the structure of the MAS are required. We survey different relevant agent-oriented methodologies and discuss their suitability in dealing with adaptation in multiagent organizations. Finally, we present some critical considerations about the analyzed methodologies together with some open issues related to the process of modeling organizations for facilitating their adaptations.

The discipline of case-based reasoning develops techniques to retrieve and reuse old solutions for new problems. To reuse solutions, several case adaptation systems have been built and many are under development. They deal with different tasks in different domains, but a methodology is still lacking. From an analysis of up-to-date case adaptation systems, this article moves towards a methodology by providing a common framework and some guidelines. As key issues case adaptation techniques, global strategies, and the tailoring of cases are discussed.

The use of robots in performance arts is increasing. But, it is hard for robots to cope with unexpected circumstances during a performance, and it is almost impossible for robots to act fully autonomously in such situations. IROS-HAC is a new challenge in robotics research and a new opportunity for cross-disciplinary collaborative research. In this paper, we describe a practical method for generating different personalities of a robot entertainer. The personalities are created by selecting speech or gestures from a set of options. The selection uses roulette wheel selection to select answers that are more closely aligned with the desired personality. In particular, we focus on a robot magician, as a good magic show includes good interaction with the audience and it may also include other robots and performers. The magician with a variety of personalities increased the audience immersion and appreciation and maintained the audience’s interest. The magic show was awarded first prize in the competition for a comprehensive evaluation of technology, story, and performance. This paper contains both the research methodology and a critical evaluation of our research.

This paper provides a historical summary of the motivations which have led several research communities to contemplate qualitative techniques. Qualitative reasoning satisfies various problem solving needs in high level decision tasks, embodied in a set of tools which allow deep knowledge to be put in compatible form with software requirements while still remaining realistic. An overview of these mathematical formalisms is presented; qualitative simulation is introduced as one of the most significant outcomes. Finally, some current research issues concerning temporal aspects of qualitative reasoning are discussed.

The paper introduces a software architecture for the specification and verification of knowledge-based systems combining conceptual and formal techniques. Our focus is component-based specification enabling their reuse. We identify four elements of the specification of a knowledge-based system: a task definition, a problem-solving method, a domain model, and an adaptor. We present algebraic specifications and a variant of dynamic logic as formal means to specify and verify these different elements. As a consequence of our architecture we can decompose the overall specification and verification task of the knowledge-based systems into subtasks. We identify different subcomponents for specification and different proof obligations for verification. The use of the architecture in specification and verification improves understandability and reduces the effort for both activities. In addition, its decomposition and modularisation enables reuse of components and proofs. Therefore, a knowledge-based system can be built by combining and adapting different reusable components.

Despite the historical difference in focus between AI planning techniques and Integer Programming (IP) techniques, recent research has shown that IP techniques show significant promise in their ability to solve AI planning problems. This paper provides approaches to encode AI planning problems as IP problems, describes some of the more significant issues that arise in using IP for AI planning, and discusses promising directions for future research.

Data mining techniques for extracting knowledge from text have been applied extensively to applications including question answering, document summarisation, event extraction and trend monitoring. However, current methods have mainly been tested on small-scale customised data sets for specific purposes. The availability of large volumes of data and high-velocity data streams (such as social media feeds) motivates the need to automatically extract knowledge from such data sources and to generalise existing approaches to more practical applications. Recently, several architectures have been proposed for what we call knowledge mining: integrating data mining for knowledge extraction from unstructured text (possibly making use of a knowledge base), and at the same time, consistently incorporating this new information into the knowledge base. After describing a number of existing knowledge mining systems, we review the state-of-the-art literature on both current text mining methods (emphasising stream mining) and techniques for the construction and maintenance of knowledge bases. In particular, we focus on mining entities and relations from unstructured text data sources, entity disambiguation, entity linking and question answering. We conclude by highlighting general trends in knowledge mining research and identifying problems that require further research to enable more extensive use of knowledge bases.

Recently there has been an increase in the number of computer aided design systems developed explicitly representing knowledge about the functionality of engineering designs. Reviewing these systems provides an understanding of the methods workers use to encapsulate knowledge of functionality within their systems. A number of issues are addressed to reveal the nature of their approaches. The developers' perception of functionality is discussed to identify variations in understanding of function and to establish the existence of any consensus. Methods of representing this knowledge are examined, thereby identifying representation types or combinations used and the advantages to be gained from any single representation. Illustrations of the manipulation of function shows how this type of knowledge can be used to support reasoning during early stage design. A survey of relationships with other design characteristics as a testimony to the manipulation of functionality is used to impact other aspects of a design. Through knowledge of relationships some models of the design process are posited by workers. A study of these bears evidence of the role of function in design and the stages at which its use is significant.

Although expert systems and knowledge engineering are attracting great attention there is still confusion about what they are. Most expert systems deal with problems which are familiar to other disciplines and their distinctive character is not always recognised. This tutorial describes the origins of expert systems in Artificial Intelligence, and the technical concept of “knowledge”. The central feature is the ideal of explicitly representing knowledge as facts, rules and other symbolic structures, rather than the traditional representation as abstract numbers or algorithms. These developments yield new solutions to old problems, and ways of solving problems whcih have previously been thought to be the preserve of the human intellect.

Decision-making is an integral part of any consideration of the discipline of control Systems. This implies feedback of knowledge in some format, whether it is mediated via human or machineoriented methods. The application of AI methodologies to control Systems engineering is described in this review under two broad categories of design and implementation. The design of control strategies is itself divided into phases of modelling and simulation, identification, and algorithm selection and tuning. The aspects of implementation which are covered include real-time considerations such as knowledge-based control and fuzzy logic, multi-sensor data fusion, fault detection and Human–Computer Interaction (HCI).

Based on a survey of recent literature, this report aims to highlight the issues associated with the verification and validation of knowledge based systems. The confusion arising from the lack of clear terminology is considered, along with some of the characteristics of knowledge based systems that cause particular difficulties for verification and validation. The various approaches that can be adopted to address these difficulties are discussed, followed by a survey of recent research initiatives.

The author concludes that many of the difficulties associated with the verification and validation of knowledge based systems are a feature of the complexity of the system being built and the manner of its development rather than of the specific technology chosen to implement it.

Ontologies are constantly evolving as new requirements daily occur and the modeling choices of the past should be updated or adapted. Exploring this evolution will enhance the understanding, augmenting the exploitation potential of the available ontologies. However, recent research focuses mostly on detecting changes between ontology versions, overloading end-users with hundreds or even thousands of changes between ontology versions, making it impossible to explore this evolution. To this direction, in this paper, we present EvoRDF, a novel framework for exploring ontology evolution using provenance queries. Our approach uses a high-level language of changes and effectively answers queries about when a specific resource was introduced and how—by which change operations. Even more, why queries can identify the sequence of changes that led to the creation of a specific resource in the latest ontology version or track the evolution of a specific resource from a past ontology version. The evaluation performed shows the feasibility of our solution and the great advantages gained.

Trust and reputation allow agents to make informed decisions about potential interactions. Trust in an agent is derived from direct experience with that agent, while reputation is determined by the experiences reported by other witness agents with potentially differing viewpoints. These experiences are typically aggregated in a trust and reputation model, of which there are several types that focus on different aspects. Such aspects include handling subjective perspectives of witnesses, dishonesty, or assessing the reputation of new agents. In this paper, we distil reputation systems into their fundamental aspects, discussing first how trust and reputation information is represented and second how it is disseminated among agents. Based on these discussions, a unifying abstraction is presented for trust and reputation systems, which is demonstrated by instantiating it with a broad range of reputation systems found in the literature. The abstraction is then instantiated to combine the range of capabilities of existing reputation systems in the Machine Learning Reputation System, which is evaluated using a marketplace simulation.

New biomedical technologies enable the diagnosis of brain tumours by using non-invasive methods. HealthAgents is a European Union-funded research project that aims to build an agent-based distributed decision support system (dDSS) for the diagnosis of brain tumours. This is achieved using the latest biomedical knowledge, information and communication technologies and pattern recognition (PR) techniques. As part of the PR development of HealthAgents, an independent and automatic classification framework (CF) has been developed. This framework has been integrated with the HealthAgents dDSS using the HealthAgents agent platform. The system offers (1) the functionality to search for distributed classifiers to solve specific questions; (2) automatic classification of new cases; (3) instant deployment of new validated classifiers; and (4) the ability to rank a set of classifiers according to their performance and suitability for the case in hand. The CF enables both the deployment of new classifiers using the provided Extensible Markup Language1 classifier specification, and the inclusion of new PR techniques that make the system extensible. These features may enable the rapid integration of PR laboratory results into industrial or research applications, such as the HealthAgents dDSS. Two classification nodes have been deployed and they currently offer classification services by means of dedicated servers connected to the HealthAgents agent platform: one node being located at the Katholieke Universiteit Leuven, Belgium and the other at the Universidad Politécnica de Valencia, Spain. These classification nodes share the current set of brain tumour classifiers that have been trained from in vivo magnetic resonance spectroscopy data. The combination of the CF with a distributed agent system constitutes the basis of the brain tumour dDSS developed in HealthAgents.

Openness is a challenging property that may characterize multi-agent systems (MAS). It refers to their ability to deal with entities leaving and joining agent society over time. This property makes the MAS behaviour complex and difficult to study and analyze, hence the need for a representative model allowing its understanding. In this context, many models were defined in the literature and we propose to classify them into three categories: structural models, functional models and interactional models. The existing models were proposed either for representing structural openness or for modelling functional or interactional ones independently. But, none of them was oriented to represent MAS openness in a global way while considering its three aspects at once. Besides, each one was defined in order to realize a specific objective and in a particular domain of application. In this paper, we propose an evolving KAGR graph. The latter provides a common understanding of openness and unifies its structural, functional and interactional aspects in a generic way. Our model is finally tested and validated on a multi-agent rescue simulator.

Networks encode dependencies between entities (people, computers, proteins) and allow us to study phenomena across social, technological, and biological domains. These networks naturally evolve over time by the addition, deletion, and changing of links, nodes, and attributes. Despite the importance of modeling these dynamics, existing work in relational machine learning has ignored relational time series data. Relational time series learning lies at the intersection of traditional time series analysis and statistical relational learning, and bridges the gap between these two fundamentally important problems. This paper formulates the relational time series learning problem, and a general framework and taxonomy for representation discovery tasks of both nodes and links including predicting their existence, label, and weight (importance), as well as systematically constructing features. We also reinterpret the prediction task leading to the proposal of two important relational time series forecasting tasks consisting of (i) relational time series classification (predicts a future class or label of an entity), and (ii) relational time series regression (predicts a future real-valued attribute or weight). Relational time series models are designed to leverage both relational and temporal dependencies to minimize forecasting error for both relational time series classification and regression. Finally, we discuss challenges and open problems that remain to be addressed.

Although they flow from a common source, the uses of multi-agent systems (or ‘agent-based computational systems’––ACE) vary between the social sciences and computer science. The distinction can be broadly summarized as analysis versus synthesis, or explanation versus design. I compare and contrast these uses, and discuss sufficiency and necessity in simulations in general and in multi-agent systems in particular, with a computer science audience in mind.

Two phenomena have probably affected modern data analysts' lives more than anything else. First, the size of real-world data sets is getting increasingly large, especially during the last decade or so. Second, modern computational methods and tools are being developed which add further capability to traditional statistical analysis tools. These two developments have created a new range of problems and challenges for analysts, as well as new opportunities for intelligent systems in data analysis.