Now showing 1 - 10 of 178
  • Publication
    Demonstrating Social Error Recovery with AgentFactory
    Exception handling is a well established method of error recovery through the alteration of plans in situ . This method relies on recovery routines existing in advance, which - we argue - is simply shorthand for more detailed plan descriptions. However, in practice, agents rarely act alone in their environment - other agents may exist, and potentially provide help in times of need. We argue that social error recovery is a particular class of exception handling that allows agents to resolve erroneous situations that are beyond their direct control. In our opinion, agent oriented programming languages must directly provide agents with abilities like social error recovery. Consequently, we introduce revisions to the AgentFactory framework, and more specifically, the programming language (AF-APL), which facilitate the rapid development of agents with in-built social error recovery. The use of these abilities are illustrated via an example of a social error recovery scenario for a mobile robot working as an office assistant.
      137
  • Publication
    Sensor fusion for social robotics
    This paper advocates the application of sensor fusion for the visualisation of social robotic behaviour. Experiments with the Virtual Reality Workbench integrate the key elements of Virtual Reality and robotics in a coherent and systematic manner. The deliberative focusing of attention and sensor fusion between vision systems and sonar sensors is implemented on autonomous mobile robots functioning in standard office environments
      251
  • Publication
    Lowering the bar for robotic development : driver generation for ubiquitous robotic systems
    (Intelligent Systems Research Centre, 2011-08-31) ;
    Robotics has developed, technologically, to a level where it becomes a field of both interest and importance to other disciplines, either as a proof-of-concept or demonstrative tool, or else as the main focus for implementation of theories. This is particularly evident in the areas of computational and theoretical cognitive science where, despite this progress, robotics remains sufficiently inaccessible to non-specialists as to dissuade its use. This is due in no small part to the issue of code re-usability across differing hardware platforms and the lack of low-level support for developing suitable drivers for the main robotics development tools. To address this issue, this work presents ACorDE: Autonomous Control Development Environment. This development environment takes in data pertaining to the robotic platform and generates suitable driver and behavioural code in a standardised format.
      1215
  • Publication
    Distributed network intelligence : a prerequisite for adaptive & personalised service delivery
    Mobile computing is undoubtedly one of the predominant computer usage paradigms in operation today. The implications of what might be cautiously termed a usage paradigm shift have still not crystallised fully, either for society, or those envisaging a new raft of applications and services for mobile users. However, fundamental to the current and future success of mobile computing are mobile telecommunications networks. Such networks have been a success story in their own right in recent years, both as traditional voice carriers and, increasingly importantly, as a conduit of mobile data. The potential for new mobile data applications is immense, but, crucially, this potential is severely compromised by two factors inherent in mobile computing: limited bandwidth and computationally restricted devices. Hence, the academic and commercial interest in harnessing intelligent techniques as a means of mitigating these concerns, and ensuring the user experience is a satisfactory one. In this paper, the broad area of intelligence in telecommunications networks is examined, and issues relating to the deployment of intelligent technologies are explored. In particular, the potential of intelligent agents is identified as a viable mechanism for realising a full end-to-end deployment of intelligence throughout the network, including possibly the most crucial component: the end user's device. As an illustration of the viability of this approach, a brief description of a mobile blogging application is presented.
    Scopus© Citations 13  1820
  • Publication
    Towards evolutionary ambient assisted living systems
    Ambient Assisted Living (AAL) is advocated as technological solutions that will enable the elderly population maintain their independence for a longer time than would otherwise be the case. Though the facts motivating the need for AAL are indisputable, the inherently heterogeneous nature and requirements of the elderly population raise significant difficulties. One particular challenge is that of designing AAL systems that can evolve to meet the requirements of individuals as their needs and circumstances change. This demands the availability of an adaptive, open, scalable software platform that incorporates a select combination of autonomic and intelligent techniques. Given that the first generation of AAL systems will be deployed in the near future, it is incumbent on designers to factor this need for evolution and adaptivity in their designs and implementations. Thus this paper explores AAL from a number of prospective and considers an agent-based middleware approach to realising an architecture for evolutionary AAL.
    Scopus© Citations 71  5984
  • Publication
    OutCare : supporting dementia patients in outdoor scenarios.
    Ambient Intelligence (AmI) is a profound vision of computing power that is invisibly embedded into the fabric of everyday life. It is accessible through intelligent interfaces which are so natural that they can be used unconsciously. The increasing maturity, performance and miniaturization of processors, networking technologies and wireless sensor networks enable a move towards pervasive computing, ubiquitous connectivity and adaptive software. The Intelligent Agent paradigm has proven itself to be a promising branch of Artificial Intelligence (AI), complementing the pervasive trend of network engineering. One of the possible usages of AmI is Ambient Assisted Living (AAL) which attempts to utilize appropriate technologies to support citizens in living in their preferred environment independently, for a longer period of time than may otherwise be the case. This paper proposes an AAL solution for Alzheimer’s patients based on the intelligent agent platform, exploring the practical delivery of intelligent environments that are sensitive and responsive to the patients, supporting them in performing daily activities and tasks in a natural, unobtrusive way.
    Scopus© Citations 15  1778
  • Publication
    Managing diversity in practical ambient assisted living ecosystems
    Though the motivation for developing ambient assisted living (AAL) systems is incontestable, significant challenges exist in realizing the ambience that is essential to the success of such systems. By definition, an AAL system must be omnipresent, tracking occupant activities in the home and identifying those situations where assistance is needed or would be welcomed. Embedded sensors offer an attractive mechanism for realizing ambience as their form factor and harnessing of wireless technologies aid in their seamless integration into pre-existing environments. However, the heterogeneity of the end-user population, their disparate needs and the differing environments in which they inhabit, all pose particular problems regarding sensor integration and management.
      473
  • Publication
    Sos: Accomodation on the fly with ACCESS
    This paper introduces Sos, a location aware and context -sensitive accommodation finding service for mobile citizens who require help finding somewhere to stay when they arrive at their chosen destination. Specifically, Sos helps users to find and book hotel accommodation that is most appropriate to their current context. This context combines the users’ current location, personal preferences, hotel availability and agenda (e.g. business meeting, tour of city). Sos has been realized as an agent-based application that has been deployed using the Agents Channelling ContExt Sensitive Services (ACCESS) architecture, an open agentbased architecture that supports the development and deployment of multiple heterogeneous context -sensitive services.
      172
  • Publication
    Clustering algorithm incorporating density and direction
    This paper analyses the advantages and disadvantages of the K-means algorithm and the DENCLUE algorithm. In order to realise the automation of clustering analysis and eliminate human factors, both partitioning and density-based methods were adopted, resulting in a new algorithm – Clustering Algorithm based on object Density and Direction (CADD). This paper discusses the theory and algorithm design of the CADD algorithm. As an illustration of its applicability, CADD was used to cluster real world data from the geochemistry domain.
    Scopus© Citations 7  906
  • Publication
    Simulating interaction with wireless sensor networks
    Wireless Sensor Networks(WSNs) are primarily regarded as data gathering entities that route data to a central server for subsequent processing. However, as WSN technologies mature and their prevalence increases, it is envisaged that a range of diverse and innovative services for mobile subscribers will be launched, of which some may require remote access and interaction with individual WSNs. Such an eventuality will give rise to additional constraints in the WSN planning and deployment processes, and raise particular challenges in the practical engineering of mobile applications and services. In this paper, a simulation tool is described. This tool enables software engineers rapidly model WSN deployments, and in this way, explore how interactions between mobile users and WSNs may occur.
      757