Vic Callaghan

Intelligent Environments: a manifesto

We explain basic features of an emerging area called Intelligent Environments. We give a short overview on how it has developed, what is the current state of the art and what are the challenges laying ahead. The aim of the article is to make aware the Computer Science community of this new development, the differences with previous dominant paradigms and the opportunities that this area offers to the scientific community and society.

A Multi-Agent Architecture For Intelligent Building Sensing and Control

We describe a new approach to intelligent building systems, that utilises an intelligent agent approach to autonomously governing the building environment. We discuss the role of learning in building control systems, and contrast this approach with existing IB solutions. We explain the importance of acquiring information from sensors, rather than relying on pre‐programmed models, to determine user needs. We describe how our architecture, consisting of distributed embedded agents, utilises sensory information to learn to perform tasks related to user comfort, energy conservation, safety and monitoring functions. We show how these agents, employing a behaviour‐based approach derived from robotics research, are able to continuously learn and adapt to individuals within a building, while always providing a fast, safe response to any situation. Finally, we show how such a system could be used to provide support for older people, or people with disabilities, allowing them greater independence and quality of life.

Some socio-technical aspects of intelligent buildings and pervasive computing research

You had to live—did live, from habit that became instinct—in the assumption that every sound you made was overheard, and…every movement scrutinized. (George Orwell, 1984) Recent reports from the European Parliament Technology Assessment unit and the UK Information Commissioners Office have highlighted the need for debate on how society should balance the convenience that new technology affords with the need to preserve privacy. To date, most of the debate has addressed the more visible aspects of technology and privacy such as surveillance cameras, identity/loyalty cards, internet search engines and radio frequency identification (RFID) tags. In this article we seek to use our experience as computer scientists to advance this debate by considering issues arising from our research related to intelligent buildings and environments, such as the deployment of autonomous intelligent agents. Intelligent buildings and environments are based on the use of numerous ‘invisible’, omnipresent, always-on, communicating computers embedded in everyday artefacts and environments. While most current intelligent building technology is based around automated reactive systems, research is under way that uses technology to gather personal information from people and use this information to deliver personalized services to them. While promising great benefits, this technology, by being invisible and autonomous, raises significant new dangers for individuals and society as a whole. Perhaps the most significant issue is privacy—an individuals right to control the collection and use of personal information. Rather than focusing on the ‘here and now’, this article looks forward to where this research could lead, exploring the issues it might involve. It does this by presenting descriptions of current work, interleaved with a set of short vignettes that are intended to provoke thought so that developers and the population at large might consider the personal and regulatory needs involved. We end this article by offering a conceptual framework for situating multidisciplinary socio-technical research in intelligent buildings.

Online learning of fuzzy behaviours using genetic algorithms and real-time interaction with the environment

This paper addresses the development of an online self-learning control system for mobile robots. In particular we describe a novel fuzzy logic and genetic algorithms (GA) method to implement a behaviour-based architecture that has significant design, analysis and performance advantages over previous approaches. We describe a new algorithm to learn fuzzy behaviours where reinforcement can be given as actions being performed. A modified version of the fuzzy classifier system (FCS) is used. The FCS is equipped with a rule-cache making it possible for the learnt expertise to be applied to future situations and to allow GA learning to start the search from the best point found. The system uses sensory information in-order to narrow the search space for the GA. The proposed techniques have resulted in rapid convergence suitable for learning individual behaviours online without need for simulation. The results of this work are compared with results reported elsewhere and reveal this approach has a superior performance to existing systems.

Towards the Next Generation of Learning Environments: An InterReality Learning Portal and Model

Advances in technology are enabling different and interesting ways of experiencing education outside the traditional classroom. For example using network technology it is possible for people to follow courses remotely via technologies such as eLearning, pod casts and 3D virtual learning environments. This paper describes research towards the integration of some cutting edge concepts, such as mixed reality, learning design, cloud learning and 3D environments that we have utilised to form a novel InterReality portal and associated pedagogical model. Our InterReality model applies Problem-based Learning (PBL) pedagogy, including co-creative learning, to the realization of a mixed reality laboratory environment for teaching embedded-computing and emerging computing applications such as the Internet-of-Things. Moreover our model proposes the use of learning design to structure the tasks and activities, their assignment to roles, and their workflow within a unit of learning (UoL) approach to allow a standardised learning activity construction, and re-use. The main contributions of this paper are the InterReality model and architecture and the supporting pedagogical analysis and rationale.

Remote Mixed Reality Collaborative Laboratory Activities: Learning Activities within the InterReality Portal

Technology is changing our way to experience education from one-dimensional (physical) to multi-dimensional (physical and virtual) education using a diversity of resources such as web-based platforms (eLearning), videoconferences, eBooks and innovative technologies (e.g. mixed reality, virtual worlds, immersive technology, etc.). This represents bigger opportunities for universities and educational institutions to collaborate with partners from around the world and to be part of todays knowledge economy. This also enables greater opportunities to experience distance learning, modifying our experience of both space and time, changing specific spatial locations to ubiquitous locations and time as asynchronous/synchronous according to our necessities. The use of virtual and remote laboratory activities is an example of the application of some of these concepts. In this work-in-progress paper we propose a different approach to the integration of the physical and virtual world by creating remote mixed reality collaborative laboratory activities within an Inter Reality Portal learning environment, thereby extending our previous progress towards these goals. The learning goal of our mixed reality lab activity is to produce Internet-of-Things-based computer projects using combinations of Cross-Reality (xReality) and Virtual objects based on co-creative and collaborative interaction between geographically dispersed students.

Explorations of Autonomy: An Investigation of Adjustable Autonomy in Intelligent Environments

There are many arguments for and against the use of autonomous-agents in intelligent environments. Some researchers maintain that it is of utmost importance to give complete control to users, and hence greatly restrict autonomy of agents, whereas, others believe that is it preferable to increase user convenience by allowing agents to operate autonomously on the users behalf. While both of these approaches have their distinct merits, they are not suitable for all users. As peoples opinions and concerns regarding agent autonomy are highly individual, depending on a wide range of factors and often changing over time, a much more dynamic approach to agent autonomy is needed. This work explores how it is possible to equip intelligent environments with an adjustable autonomy mechanism, which allows an individual user to increase or decrease agent autonomy in order to find their own comfortable sweet-spot between maintaining/relinquishing control and gaining/losing convenience. This paper presents the Adjustable Autonomy Intelligent Environment (AAIE) model, discusses how adjustable autonomy can be achieved in intelligent environments, and discusses the major findings from a recent online survey and user study, which highlight the major factors and concerns of users that determine their personal preferences towards different levels of autonomy.

Looking Back in Wonder: How Self-Monitoring Technologies Can Help Us Better Understand Ourselves

As computing devices become more pervasive, our daily activities start generating a vast amount of information that could be exploited for helping us better understand ourselves. In this paper we present a system that uses easily available data correlated into a story-based representation aimed at providing users with a better understanding of their lifestyles. While this is still work in progress, we believe that it provides valuable insights into the design of such systems. Our initial findings show that user data generated through a person’s daily activities can reveal a wealth of valuable information which they can use to adjust and improve their lifestyles.

HIERARCHICAL BEHAVIOURAL CONTROL FOR AUTONOMOUS VEHICLES

Abstract The subject of this paper is the control of autonomous vehicles. A hierarchical approach is studied in the context of fuzzy systems and a programming language for the mid to low level control of autonomous vehicles is described. The language, called FDTL (Fuzzy Decision Tree Language), is based on a computational model that combines fuzzy rule based control with the hierarchical nature of decision trees.

iWorlds: Generating artificial control systems for simulated humans using virtual worlds and intelligent environments

This paper highlights research into using virtual worlds, intelligent environments and mixed reality to create artificial control systems for simulated humans. Following a brief explanation of this project, the beneficial contribution provided by virtual worlds, intelligent environments and mixed reality systems is outlined. Throughout this project a series of experimental iWorlds, (virtual and mixed reality intelligent environments) have been used to profile the actions and decisions of humans to generate sets of realistic behaviours and test the project research hypothesis. These worlds consist of a mixed-reality household experiment plus two supporting game-like behaviour experiments, namely ‘Bar-World’ and ‘Battleships’ which were designed to explore and reinforce aspects of the underlying theory. As a core part of this work a description of a new profile generation mechanism is presented, which comprises a genetic programming mechanism that blends real user behaviour data to produce varied artificial profiles for non-player computer characters. In support of this a set of experimental results are presented that reveal the new artificial intelligence mechanism does indeed advance the project aim to create realistic simulated humans. A discussion is included that describes the potential benefits that could be gained by incorporating these methodologies into computer games and professional intelligent environment development systems.