Ruth Aylett

Heriot-Watt University · School of Mathematical and Computer Sciences

Using empathic virtual agents for Personal and Social Education is a powerful and immersive way to sensitise students for the problems and dangers related to persistent aggressive behaviour among students, also known as bullying. The work reported here relates to the evaluation of applying such agents in schools in the UK, Portugal, and Germany as...

An abstract is not available.

In this paper we consider the role of story in digital technology enhanced learning and the issues involved in constructing digital narrative learning environments. We will see that story has played an important role in education for a very long time, well pre-dating the use of digital technologies, and can be closely related to a number of theoret...

Edutainment 2006 is an international conference on research and development on e-learning and digital entertainment. The main purpose of the conference is the d- cussion, information and opinions exchange on the development and use of such s- tems. It provides a very interesting opportunity for researchers who want to attend or present communicatio...

The origin of the Intelligent Virtual Agents conference dates from a successful workshop on Intelligent Virtual Environments held in Brighton, UK at the 13th European Conference on Arti?cial Intelligence (ECAI’98). This workshop was followed by a second one held in Salford in Manchester, UK in 1999.Subsequent events took place in Madrid, Spain in 2...

This paper examines the causes and consequences of the narrative paradox phenomenon widely ob served in VR. We present an alternative approach to virtual and interactive storytelling in the form of the e mergent narrative concept, together with an implementation of a subset of these ideas in the FearNot! demonstrator.

The Aective Guide System is a mobile context-aware and spatial-aware system, oering the user with an aective multimodal in- teraction interface. The system takes advantage of the current mobile and wireless technologies. It includes an 'aective guide with attitude' that links its memories and visitor's interest to the spatial location so that stori...

This paper considers affective interactions to achieve empathic en- gagement with synthetic characters in virtual learning environments, in order to support and induce the expression of empathy in children. The paper presents FearNot!, a school based virtual learning environment, populated by synthetic characters used for personal, social and healt...

The Emergent Aective and Personality model is a body- mind model of emotions for a mobile tour guide agent. This research is inspired by work in Psychology, Brain Research, Personality, Narra- tive, Mobile Computing and Artificial Intelligence. The main goal is to build an 'intelligent guide with attitude'. This paper presents a review of related w...

We discuss the experience of constructing the application FearNot! (Fun with Empathic Agents Reaching Novel Outcomes in Teaching), an applica- tion of virtual drama to anti-bullying education inspired by Forum Theatre. An appraisal-driven agent architecture is presented as a mechanism for generating an emergent, that is, unscripted, narrative. A sm...

This paper discusses a study in supporting collaborative military planning in which groupware, video-conferencing and a desktop Collaborative Virtual Environment (CVE) were used. It discusses the design and implementation of the CVE and the setup and execution of the study using questionnaires and observation. The results of the study questionnaire...

This paper introduces our approach to apply synthetic characters to behavior training in primary schools. Project groups include research centers from UK, Portugal, and China. Research members include artificial intelligent group, graphical group, educational group and psychological group. 24 months co-operation work and 4 meetings exchanging idea...

Virtual environments (VEs) are now becoming a promising new technology to be used in the development of interactive learning environments for children. Perhaps triggered by the success of computer games, VEs are seen as an emergent and engaging new way by which children can learn experimental sciences and other disciplines. Inhabiting these IVEs ca...

We discuss work carried out at the University of Salford (UK) and INESC-id (Portugal) on the design and implementation of interactive dramas in D graphics environments. We present detailed requirements and methods for the design of unscripted (emergent) dramas based on research into role-playing games. We describe the affectively driven intelligent...

The origin of the Intelligent Virtual Agents conference dates from a successful workshop on Intelligent Virtual Environments held in Brighton at the 13th European Conference on Artificial Intelligence (ECAI'98). This workshop was followed by a second one held in Salford in Manchester in 1999. Subsequent events took place in Madrid, Spain in 2001 an...

This paper describes our proposal for storytelling in virtual environments from a virtual guide perspective, detailing the involved knowledge representation and algorithms. In our model the guide begins at a particular location and starts to navigate the world telling the user stories related to the places she visits. Our guide tries to emulate a r...

The MY virtual graffiti (MYVG) system is an artistic medium that uses two sensor gloves, a six degree of freedom hand-held controller (Space Orb 360deg), a tracking system and dummy spray can nozzle strokes to create graffiti in a fully immersive CAVE environment. It redefines the traditional communication and art form of graffiti using virtual rea...

This paper presents an ethologically inspired actionselection mechanism, part of a larger architecture for selfanimated artificial animals (agents) that communicate emotions to each other, influencing each other's behaviour. The problem of action selection is that of choosing at each moment in time the most appropriate action out of a repertoire of...

When building agents and synthetic characters, and in order to achieve believability, we must consider the emotional relations established between users and characters, that is, we must consider the issue of "empathy". Defined in broad terms as "An observer reacting emotionally because he perceives that another is experiencing or about to experienc...

Grid technology has been widely used for large-scale computational problems, but it also provides a framework for running a big number of smallsized processes. Moreover, these processes can take advantage of the Grid facilities like security, fault tolerance, or load balancing.

We discuss the FearNot! application demonstrator, currently being developed for the EU framework V project VICTEC. It details the language structure, content, interactions management and design of the FearNot! Demonstrator, as well as presenting the VICTEC project and its motivations.

This paper discusses why intelligent embodied agents – concentrating on the case of graphically-embodied agents – require affective systems. It discusses the risks involved in attempting to produce naturalistic expressive behaviour, and examines the specific case of facial expression generation. It considers the approach taken by the EU Framework 5...

This paper makes two contributions to increasing the en- gagement of users in virtual heritage environments by adding virtual living creatures. This work is carried out on the context of models of the Mayan cities of Palenque and Calakmul. Firstly, it proposes a virtual guide system. The guide navigates a virtual world and tells stories about the l...

This paper briey describes our proposal for storytelling in virtual environments from a virtual guide perspective. In our model the guide begins at a particular location and starts to navigate the world telling the user stories related to the places she visits. Our guide tries to emulate a real guide's behaviour in such a situation. In particular,...

This paper presents an ethologically inspired actionselection mechanism, part of a larger architecture for selfanimated artificial animals (agents) that communicate emotions to each other, influencing each other’s behaviour. The problem of action selection is that of choosing at each moment in time the most appropriate action out of a repertoire of...

This paper aims at reviewing narrative approaches and theories in an effort to assess their potential as suitable models for computational implementation within the EU Framework V-funded project VICTEC (Virtual ICT with Empathic Characters). We discuss classical narrative theories as well as envisage alternative interactive models according to the...

When building agents and synthetic characters, and in order to achieve believability, we must consider the emotional relations established between users and characters, that is, we must consider the issue of "empathy". Defined in broad terms as "An observer reacting emotionally because he perceives that another is experiencing or about to experienc...

The FearNot! application demonstrator, currently being developed for the EU framework V project VICTEC, uses empathic agents as a basic mechanism for engaging children in anti-bullying education. The empathic agents are driven by an affective system in interactional dramas in which both physical actions and language actions are required. This paper...

This paper describes our proposal for storytelling in virtual environments from a virtual guide perspective, detailing the involved knowledge representation and algorithms. In our model the guide begins at a particular location and starts to navigate the world telling the user stories related to the places she visits. Our guide tries to emulate a r...

Virtual Reality (VR), by its nature and characteristics, is of specific interest to the AI community, particularly in the domains of Storytelling and Intelligent Characters. We argue that VR must be considered a particular narrative medium alongside Theatre, Literature or Cinema. This paper reviews relevant work in narrative theory from Plato onwar...

We present an Action Selection Mechanism inspired by ethology and theories of emotion. We consider how emotions - using fear as an example - affect the behaviour of artificial animals, in this case deer and sheep, as paradigmatic flocking mammals. We show how olfaction can be used to communicate emotion amongst conspecifics, through pheromones mode...

This paper discusses the use of intelligent planning as a control mechanism for agents situated in a virtual world. Virtual environments require a planning system that is flexible enough to handle situations impossible to predict before execution has started. In order to produce believable results, the planner should also be able to model and handl...

This paper discusses preliminary work on an ongoing project aiming towards the development of a three-dimensional, emergent narrative environment driven by a hierarchical continuous planning system. In contrast to most existing similar systems, the proposed approach assumes the lack of a solid set of initial goals for the user agent and relies almo...

This paper describes our proposal for storytelling in virtual environments from a virtual guide perspective. In our model the guide begins at a particular location and starts to navigate the world telling the user stories related to the places she visits. Our guide tries to emulate a real guide’s behaviour in such a situation. In particular, she be...

The consideration of the narrative question within Virtual Environments (VEs) is a compromise regarding to the conflict between pre-authored narrative structures and user freedom both in terms of interaction and physical movement. By presenting the results of a recent investigation on the narrative structures and mechanisms of Role Playing Games (R...

This paper extends Reynolds’ flocking algorithm to incorporate the effects of emotions, in this case fear. Sheep are used as a typical example of flocking mammals and an autonomous agent architecture with an action selection mechanism incorporating the effects of emotion is linked to the standard flocking rules. Smell is used to transmit emotion be...

In this paper we describe an emotional-behvioral architecture. The emotional engine sits at a higher layer than the behavior system, and can alter behavior patterns, the engine is designed to simulate Emotionally-Intelligent Agents in a Virtual Environment, where each agent senses its own emotions, and other creature emotions through a virtual smel...

KA-Tool embodies work aimed at allowing domain experts to generate a domain model for an AI planning system, carried out as part of a larger project to build an integrated set of tools for supporting AI planning. In this paper, after an overview of the knowledge acquisition process, we describe an implemented induction process. This uses a set of p...

In this paper, we introduce an ongoing research project, which aims at developing an immersive storytelling environment. In such a system, which is inspired from the "Holodeck" device, human users will be able to interact with artificial actors through speech, while sharing the same physical environment. Once on the set, the users will be able to p...

The paper discusses work in progress on a multi-agent system combining a reflective agent containing a predictive planner and working at a symbolic level with a number of behavioural robotic agents driven at a non-symbolic level by sensor data. It examines whether in the light of this work it appears possible to abstract a planner from the executio...

The paper describes work-in-progress in extending a behavioural agent architecture to include a low-level emotional system and communication of emotions between agents using virtual odour for propagation.

This paper describes an on-going study which applies the concept of transitivity to news discourse for text processing tasks.

This paper discusses work aimed at allowing domain experts to generate a domain model for an AI planning system as part of a larger project to build an integrated set of tools for supporting AI planning. It outlines the overall methodology and discusses the tool in which this is embodied. A Domain model is generated in which can be represented by c...

Our work aims to support domain experts in the knowledge acquisition phase. The methodology applies the PLANFORM-KA model supporting the encoding of interviews with domain experts or their direct interaction. A Domain model is generated in which a cluster of constraints take place to shape an Ontology of each studied case. Progress has been made to...

KA Tool embodies work aimed at allowing domain experts to generate a domain model for an AI planning system, carried out as part of a larger project to build an integrated set of tools for supporting AI planning. The paper outlines the overall methodology and describes how KA Tool supports it. A Domain model is generated in which can be represented...

In this paper we describe BAMUVA. BAMUVA is Robot based behavioural architecture designed to create Intelligent Agents in a Virtual Environment, where each agent senses obstacles and other moving creatures in the environment and reacts to them. The architecture consists of a Behaviour layer, a motor layer and a library of sensors. Keywords: Agents,...

The paper describes a project to develop virtual environment-based TeleTubby characters, as in the chidrens' TV programme. The differences between the media are considered and the requirements for character development. The multi-level architecture, BALSA, adopted is described in detail and future developments are proposed.

In this paper we describe an emotional- behavioural architecture. The emotional engine is a higher layer than the behaviour system, and it can alter behaviour patterns, the engines is designed to simulate Emotionally-Intelligent Agents in a Virtual Environment, where each agent senses its own emotions, and other creature emotions through a virtual...

In this paper we describe an emotional- behavioural architecture. The emotional engine is a higher layer than the behaviour system, and it can alter behaviour patterns, the engine is designed to simulate Emotionally-Intelligent Agents in a Virtual Environment, where each agent senses its own emotions, and other creature emotions through a virtual s...

Knowledge engineering in AI planning is the process that deals with the acquisition, validation and maintenance of planning domain models, and the selection and optimization of appropriate planning machinery to work on them. Our long term aim is to research and develop rigorous methods for the acquisition, maintenance and validation of planning dom...

Reearch into virtual environments on the one hand and artificial intelligence and artificial life on the other has largely been carried out by two different groups of people with different preoccupations and interests, but some convergence is now apparent between the two fields. Applications in which activity independent of the user takes place ---...

As the number of deployed multi-agent applications increases, further and better experience with the technology is gained, enabling a strong evaluation of the field from a more practical perspective. In particular, questions relating to how the theory of multi-agent systems impacts on practice, and how the practical development itself compares with...

Introduction One of the main reasons for the sustained activity and interest in the field of agent-based systems, apart from the obvious recognition of its value as a natural and intuitive way of understanding the world, is its reach into very many different and distinct fields of investigation. Indeed, the notions of agents and multi-agent systems...

1. Why and how VEs and AI/Alife technologies are converging In this report we consider a new field we call Intelligent Virtual Environments, formed by the increasing overlap of the technologies involved in 3D real-time interactive graphics environments and Artificial Intelligence/Artificial Life technologies. The impetus for this field comes from a...

Predicting the future is a risky game, and can often leave egg on one’s face. However when the organizers of the Intelligent Virtual Environments workshop at the European Conference on AI predicted that the field of Intelligent Virtual Agents would grow and mature rapidly, they were not wrong. From this small workshop spawned the successful one on...

Research at the University of Salford is currently focusing upon the problem of generating plans for multiple autonomous agents which cooperatively carry out various complex tasks. This paper reports work in progress. We discuss the use of predictive planning, embodied in a computerbased reflective agent, to provide a supervisory user interface to...

Research at the University of Salford is focusing upon the construction of a hybrid multi-agent system involving a computer-based Reflective Agent (RA) which incorporates the predictive planner UCPOP and directs a number of behavioural agents (BAs) running a novel behavioural control architecture, the BSA. This paper outlines the BSA and discusses...

This paper argues that AI planning is a technology ripe for use on real world problems as shown by a number of current applications. An introduction is given to AI planning, and then followed by discussion of the successful application of this technology to generating operating procedures for chemical plants. A description is given of the methodolo...

From time to time, the convergence of new technologies and research communities at key points in their development provides a renewed impetus to further progress in their separate fields, to cross-fertilization of ideas and techniques with one inspiring the other, and to the emergence of new areas for research and new application areas. This is exa...

This paper argues that AI planning is a technology ripe for use on real world problems as shown by a number of current applications. An introduction is given to AI planning, and then followed by discussion of the successful application of this technology to generating operating procedures for chemical plants. A description is given of the methodolo...

All industrial plants require an extensive set of operating procedures. This paper discusses the use of hierarchical nonlinear least-commitment AI planning technology to generate plant operating procedures for chemical process plant. It considers the handling of flow through the interfacing of a valve sequencing subplanner, the handling of safety t...

The paper discusses an architecture for an agent carrying out continuous planning, in which planning and execution are interleaved and agent motivations are used to generate goals. The agent may pass actions to a number of other agents for execution. The architecture is discussed in the context of the running of a water-processing laboratory in whi...

Operating procedure synthesis (OPS) has been used to generate plant operating procedures for chemical plants. However, the application of AI planning to this domain has been rarely considered, and when it has the scope of the system used has limited it to solving “toy” problems. This paper describes the application of state-of-the-art AI planning t...

We discuss the use of variables during the planning process as means of extending the use of least commitment. We describe how static relationships can be treated as constraints between variables, which we call `pairs', can improve both the efficiency of the planning process and the modelling expressiveness of planning operators.

The past ten years has seen a flurry of research activity into the behavioural control of autonomous mobile robots. Yet despite this effort, many researchers are of the opinion that behavioural robots are incapable of achieving tasks more complex than simple can collecting, box pushing, herding or moving in formation. If such robots are to gain ind...

UK Robotics Ltd. have for some time been working in the area of multiple co-operant autonomous mobile robots. While there are a number of applications in the nuclear, chemical and o#-shore industries that would bene#t from such technology, the required science and engineering is only just beginning to be realised. The key issues are #rstly,howtocon...

Salford University has for some time been working in the area of multiple co-operant autonomous mobile robots. While there are a number of applications for this technology in remote hazardous environments, suchasrover based planetary exploration, the required science and engineering is only just beginning to be realised. The key questions are #rstl...

spectrum is emotion as a cognitive state, while for those working at the more physical end it is emotion as a bodily state. Note that by this we mean the internal modelling of emotion, rather than its external expression. These two approaches reflect a longstanding debate within psychology itself [Picard 97] and could be traced back as far as the s...

An abstract is not available.

In this paper we consider the clash between the pre-scripted character of much narrative and the freedom afforded by a Virtual Environment. We discuss the concept of emergent narrative as a possible way of avoiding this clash. We examine the role of a VE user in a narrative and consider the concept of social presence as a means of reconciling the f...

Operating Procedure Synthesis (OPS) has been used to produce operating procedures for chemical plants. This paper discusses the issues that must be addressed in using AI Planning for this task, using a simple example. It shows how a state-of-the-art least commitment planner with goals of prevention', CEP, the Chemical Engineering Planner, deals wit...

There has been little published on the development of operators for AI planners, even though it is a difficult task.This paper addresses this important issue by looking at the requirements of the language used to describe operators, the methodology behind the synthesis of operators, and tools that could be used to aid in their development. The majo...

This paper discusses how far the characteristics of the execution systems impact the planner which plans for them. It does this in the context of the MACTA project in which multiple cooperating mobile robots running a behavioural architecture are integrated with a Reflective Agent based on a computer running a symbolic planner, in this case UCPOP....

We present a formal model of negotiation between autonomous agents. The purpose of the negotiation is to reach an agreement about the provision of a service by one agent for another. The model defines a range of strategies and tactics that agents can employ to generate initial offers, eveluate proposals and offer counter proposals. The model is bas...

This paper discusses the issues involved in applying a generic AI planner to the problem of generating plant operating procedures for chemical process plant. It considers the problem of providing the correct planning facilities, concentrating on dealing with flow of chemicals, and proposes the use and integration of a special purpose planner for va...

This paper discusses how far the characteristics of the execution systems impact the plannerwhich plans for them. It does this in the context of the MACTA project in which multiple cooperatingmobile robots running a behavioural architecture are integrated with a Reflective Agentbased on a computer running a symbolic planner, in this case UCPOP. The...

Operating Procedure Synthesis (OPS) has been used to produce operating procedures for chemical plants. However, the application of AI planning to this domain has rarely been considered, and when it has the scope of the system used has limited it to solving ‘toy’ problems. This paper describes a case study for the INTergrating OPerability (INT-OP) p...

This paper reports on the issues involved in the design of a planner for a particular class of real world domains, the domains that involve the operation of chemical processing plants. We analyse the unique difficulties faced when planning in these domains. These difficulties centre around the problem of modelling the creation of a flow of chemical...

UK Robotics Ltd. have for some time been working in the area of multiple co-operant autonomous mobile robots. While there are a number of applications in the nuclear, chemical and off-shore industries that would benefit from such technology, the required science and engineering is only just beginning to be realised. The key issues are firstly, how...

Work at Salford into a behavioural approach to multiple cooperating robots has resulted in the Behaviour Synthesis Architecture, in which cooperation emerges from the combining of behaviours at `self', `environment ', `species' and `universe' levels using a utility function. While this has been successfully applied to low-level cooperation, the nee...