Online Learning and Adaptation for Intelligent Embedded Agents Operating in Domestic Environments

Intelligent association selection of embedded agents in intelligent inhabited environments

“…These concepts were explored in various projects such as the intelligent Dormitory (iDorm) which at the same time forms a test bed for the IIE research. Many approaches have been presented and analysed for online learning and adaptation of the agents embodied in the iDorm such as the ISL [17,18] and AOFIS [7]. Both ISL and AOFIS employed fuzzy logic based embedded agents that seek to particularise (rather than generalise) to the specific user needs and respond immediately to whatever the end user demands (providing it does not violate any safety constraints).…”

“…Moreover, FLCs provide an adequate methodology for designing robust controllers that are able to deliver a satisfactory performance when contending with the uncertainty, noise and imprecision attributed to real world environments as in IIEs. As a result FLCs have been used in IIEs as in [7,17,18].…”

“…The iDorm looks and feels like an ordinary study/bedroom environment containing a mix of furniture such as a bed, work desk and wardrobe. This splits the room into areas of different activity such as sleeping, working and entertaining [17,18,22]. The iDorm has a standard multi-media PC that combines a flat screen monitor and a multi-media video projector which can be used for both working and entertainment.…”

“…It is ubiquitous because the user is surrounded by a multitude of interconnected embedded systems which form a pervasive infrastructure. Its transparency is due to the invisible nature of the computing based artefacts being seamlessly integrated into the surrounding environment [3,17,18]. Embedded agents can provide the intelligent 'presence' as they are able to recognise the users and can autonomously program themselves to the users' needs and preferences by learning from their behaviour to control the environment on their behalf.…”

“…The agents will reduce the number of associations and interconnections to the other devices and embedded agents to minimise the network overheads and the unneeded extra processing created by the redundantly associated devices while satisfying the environment and the user personalised needs. The intelligent embedded agents are based on the Fuzzy Logic Controller (FLC) which has been credited with providing an appropriate framework for generating human readable models for complex systems [17,18]. FLCs provide an adequate methodology for designing robust controllers that are able to deliver a satisfactory performance when contending with the uncertainty, noise and imprecision attributed to real world environments as in IIEs.…”