O'Hare, G. M. P. (Greg M. P.)
O'Hare, G. M. P. (Greg M. P.)
O'Hare, G. M. P. (Greg M. P.)
Now showing 1 - 10 of 178
- PublicationDynamic choice of robust strategies in dialogue managementAn important tradeoff in error-prone dialogue is between the cost of using more robust dialogue strategies and the cost of recovering from failed understanding without using them. A strategy has to be quantitatively planned for each dialogue state, since too robust a strategy might not have a worthwhile effect on the failure rate. A dialogue manager is described which chooses between strategies that have differing levels of robustness with a view to maximising the efficiency of the dialogue
- PublicationTowards Holistic Activity Modeling and Behavioral AnalysesAs the age profile of many societies continues to increase, supporting health, both mental and physical, is of increasing importance if independent living is to be maintained. Sensing and, ultimately, recognizing activities of daily living has been perceived as a prerequisite for detecting tasks that people avoid or find increasingly difficult to perform, as well as being indicators of certain illnesses. To date, extensive research efforts have been made on activity monitoring, recognition and assistance in indoor scenarios, frequently through smart home initiatives. However, the scenarios outside of the home have not received a similar degree of attention from the research community. This paper advocates a need for platforms that enable activity recognition in a range of environments, thus enabling the construction of more complex yet realistic activity models and behavior patterns. The design of a prototype supporting an integrated approach to sensor data capture and activity model construction is proposed. The application domain is that of dementia.
- PublicationWhat is a social robot?This paper discusses the concept of a social robot. Developing from recent work on physical embodiment, the necessity for a socially embodied robot is presented. Current work via the Social Robot Architecture seeks to develop and demonstrate these concepts.
- PublicationManaging mobile-based participatory sensing communitiesParticipation of mobile phone users in sensorial data collection both from the individual and from the surrounding environment presents a wide range of opportunities for truly pervasive applications. This paper highlights relevant issues related to mobile-phone participatory sensing and describes an architecture framework to flexibly create new communities of data interest, to manage and interact with those communities and to finally provide useful information to the users.
- PublicationEmbedding Agents within Ambient Intelligent ApplicationsThis chapter reflects upon the challenges that confront the deployment of Ambient Intelligence (AmI) applications. Ambient Intelligence demands that everyday artefacts be imbued with intelligent reasoning capabilities together with the capacity for collaborative intelligent behaviour. Traditional ambient devices do not provide the requisite computational platform to support such requirements. With the ongoing developments of ubiquitous devices, however, the situation is changing. This chapter discusses a software stack, which supports the needs of ambient applications that incorporate embedded intelligence.
- PublicationBrowsing the Sensor Web : Pervasive Access for Wide-area Wireless Sensor NetworksWireless Sensor Networks (WSNs) are almost exclusively regarded as data gathering entities. Various sensed data elements are captured and routed back to a central server for processing, visualization and interpretation. However, it can be realistically conjectured that scenarios will increasingly emerge that demand a facility for ad-hoc interaction with individual sensor nodes. Moreover, such interaction will occur in the physical environment in close proximity to where the sensor node is physically located. In this paper, the need for in-situ ad-hoc interaction is motivated. A methodology for facilitating such interaction is presented, and the implementation of a sensor browser is described.
- PublicationImplicit interaction : a prerequisite for practical AmIIntelligent User Interfaces represent one of the three distinguishing characteristics of AmI environments. Such interfaces are envisaged as mediating between the services available in an arbitrary physical environment and its inhabitants. To be effective, such interfaces must operate in both proactive and passive contexts, implicitly and explicitly anticipating and responding to user requests. In either case, an awareness of the prevailing situation is essential – a process that demands a judicious combination of data and decision fusion, as well as collaborative and centralized decision making. Given the constraints of AmI environments realizing a distributed lightweight computational infrastructure augmented with a need to address user needs in a timely manner poses significant challenges. In this paper, various issues essential to enabling seamless, intuitive and instinctive interaction in AmI environments are explored.
- PublicationAgent factory: towards social robotsThis paper advocates the application of multi-agent techniques in the realisation of social robotic behaviour. We present the Social Robot Architecture, which integrates the key elements of agent-hood and robotics in a coherent and systematic manner. This architecture seamlessly integrates, real world robots, multi-agent development tools, and VRML visualisation tools into a coherent whole. Using these elements, we deliver a development environment, which facilitates rapid prototyping of social robot communities
- PublicationAF-ABLE in the Multi Agent Contest 2009This is the second year in which a team from University College Dublin has participated in the Multi Agent Contest. This paper describes the system that was created to participate in the contest, along with observations of the team's experiences in the contest. The system itself was built using the AFAPL agent programming language running on the Agent Factory platform. A hybrid control architecture inspired by the SoSAA strategy aided in the separation of concerns between low-level behaviours (such as movement and obstacle evasion) and higher-level planning and strategy.