Nicolas Sabouret

An Overview of Semantic Web Services Composition Approaches

In this paper, we are motivated by the problem of semantic web services composition. We first present a typical example requiring services composition, give a definition of an automated services composition approach and outline its main requirements. We then discuss existing techniques and their limitations with regards to those requirements. Finally, we present our proposal for web services composition based on autonomous services interactions.

The TARDIS Framework: Intelligent Virtual Agents for Social Coaching in Job Interviews

The TARDIS project aims to build a scenario-based serious-game simulation platform for NEETs and job-inclusion associations that supports social training and coaching in the context of job interviews. This paper presents the general architecture of the TARDIS job interview simulator, and the serious game paradigm that we are developing.

Mechanisms for environments in multi-agent systems: Survey and opportunities

The environment has been recognized as an explicit and exploitable element to design multi-agent systems (MAS). It can be assigned a number of responsibilities that would be more difficult to design with the sole notion of agents. To support the engineering of these responsibilities, we identify a set of mechanisms that offer solutions to software designers. We describe the mechanisms, their usage in representative projects, and potential opportunities for further research and applications. The purpose of this article is to clarify the notion of environment in terms of mechanisms, from their abstract description to their practical exploitation. Mechanisms are expected to provide agent-based software designers with a set of design elements to build MAS that take advantage of the environment.

Overhearing and Direct Interactions: Point of View of an Active Environment

Overhearing has been proposed recently as a model of indirect interactions in Multi-Agent Systems. Overhearer agents receive messages that were not primarily sent to them, as when someone hears a conversation among others. Overhearing has been modeled essentially as message broadcasting, but this approach raises several issues of scalability and appropriateness of the mental state of overheard agents. In this paper, we motivate and propose a model of overhearing that copes with these issues by introducing an explicit environment entity to handle overhearing. We define key notions with focus on the environment perspective, model them and their relations, and detail an algorithm that describes the environmental process for agent interactions. We finally illustrate our approach with an electronic market scenario.

An Emotional Model for Synthetic Characters with Personality

In recent years, emotional computing has found an important application domain in the field of interactive synthetic characters. Interesting examples of this domain are computer games, interface agents, human-robot interaction, etc. However, few systems in this area include a model of personality, although it plays an important role in differentiating agents and determining the way they experience emotions and the way they behave.

Environmental support for tag interactions

Tag interactions are agent interactions that complement and differ from speech act communication models. Tags are public information that agents expose to others in the system to allow two types of interactions. Tag monitoring interactions let agents observe the tags of others actively. Tag fortuitous interactions make agents realize the tag of others with unrequested and application-dependent messages. In this paper we model tag interactions based on the agent environment and computational bodies to enact, maintain, and regulate their execution. We discuss the model and we identify further issues in the current state of the research. An example application is described in detail to show the potential of introducing tag interactions.

Dynamic service composition enabled by introspective agent coordination

Service composition has received much interest from many research communities. The major research efforts published to date propose the use of service orchestration to model this problem. However, the designed orchestration approaches are static since they follow a predefined plan specifying the services to be composed and their data flow, and most of them are centralized around a composition engine. Further, task decomposition is made prior to service composition, whereas it should be performed according to the available competencies. In order to overcome these limitations, we propose to model a dynamic approach for service composition. The studied approach relies on the decentralized and autonomous collaboration of a set of services whose aim is to achieve a specific goal. In our work, this goal is to satisfy requirements in software services that are freely expressed by human users (i.e. not predefined through a composition plan). We propose to enable the service collaborations through a multi-agent coordination protocol. In our model, agents offer services and are endowed with introspective capabilities, that is, they can access and reason on their state and actions at runtime. Thereby, the agents are capable of decomposing a monolithic task according to their service skills, and dynamically coordinating with their acquaintances to cover the whole task achievement. This paper presents the adaptive agent-based approach we propose for dynamic service composition, describes its architecture, specifies the underlying coordination protocol, called omposer, verifies the protocol’s main properties, and validates it by unfolding an implemented scenario.

Generic command interpretation algorithms for conversational agents

This paper focuses on human-machine communication with intelligent agents, it proposes a generic architecture with an algorithm for natural language (NL) command interpretation which makes it easy to define different applications using the description and domains of the different agents, since all that is required is their respective codes and domain ontologies. There are two classical approaches for NL command interpretation: the top-down approach, which relies on the syntactical constraints of the agents model, and the bottom-up approach which relies on the set of the agents possible actions. The present work combines the two in a new bottom-up based algorithm that makes use of agents constraints. The three algorithms are then compared, and results show that the combined approach gives best results.Software reuse can provide significant improvements in software productivity and quality whilst reducing development costs. Expressing software reuse intentions can be difficult though. A developer may aspire to reuse a software component but experience difficulty expressing their reuse intentions in a manner that is compatible with, or understood by, the component retrieval system. Various intelligent retrieval techniques have been developed that assist a developer in locating or discovering components in an efficient manner. These solutions share a common shortcoming: the developer must be capable of anticipating all reuse opportunities and initiating the retrieval process. There is a need for a comprehensive technique that not only assists with retrievals but that can also identify reuse opportunities. This paper advocates that component-based reuse can be supported through knowledge collaboration. Often programming tasks and solutions are replicated; this characteristic of software can be exploited for the benefit of future developments. Through the mining of existing source code solutions, knowledge, relating to how components are used by developers, can be extracted. Based on a developer’s current programming task, this knowledge can subsequently be filtered and used to recommend a candidate set of reusable components. This novel recommendation approach applies and extends commonly used Information Retrieval and Information Filtering techniques such as Collaborative Filtering, Content-Based Filtering, and Bayesian Clustering Models, to the software reuse domain. This recommendation technology is applied to several thousand open-source Java classes. The most effective recommendation algorithm produces recommendations of a high quality at a low cost.

Prediction of Humans' Activity for Learning the Behaviors of Electrical Appliances in an Intelligent Ambient Environment

In this paper we propose a mechanism of prediction of domestic human activity in a smart home context. We use those predictions to adapt the behavior of home appliances whose impact on the environment is delayed (for example the heating). The behaviors of appliances are built by a reinforcement learning mechanism. We compare the behavior built by the learning approach with both a merely reactive behavior and a state-remanent behavior.

Towards a Socially Adaptive Virtual Agent

This paper presents a socially adaptive virtual agent that can adapt its behaviour according to social constructs (e.g. attitude, relationship) that are updated depending on the behaviour of its interlocutor. We consider the context of job interviews with the virtual agent playing the role of the recruiter. The evaluation of our approach is based on a comparison of the socially adaptive agent to a simple scripted agent and to an emotionally-reactive one. Videos of these three different agents in situation have been created and evaluated by 83 participants. This subjective evaluation shows that the simulation and expression of social attitude is perceived by the users and impacts on the evaluation of the agent’s credibility. We also found that while the emotion expression of the virtual agent has an immediate impact on the user’s experience, the impact of the virtual agent’s attitude expression’s impact is stronger after a few speaking turns.