http://hdl.handle.net/10149/47235 Sat, 18 May 2013 22:41:24 GMT 2013-05-18T22:41:24Z http://hdl.handle.net/10149/250961 Title: Revealing complexity through domain-specific modelling and analysis Authors: Paige, R. F. (Richard); Brooke, P. J. (Phillip); Ge, X. (Xiaocheng); Power, C. (Christopher); Burton, F. R. (Frank); Poulding, S. (Simon) Abstract: Complex systems exhibit emergent behaviour. The explanations for this explicit emergent behaviour are often difficult to identify, and usually require understanding of significant parts of system structure and component behaviour to interpret. We present ongoing work on a set of techniques, based on Model-Driven Engineering principles and practices, for helping to reveal explanations for system complexity. We outline the techniques abstractly, and then illustrate parts of them with three examples from the health care, system security and Through-Life Capability Management domains. Sun, 01 Jan 2012 00:00:00 GMT http://hdl.handle.net/10149/250961 2012-01-01T00:00:00Z http://hdl.handle.net/10149/250353 Title: Evolving body kinematics for virtual characters Authors: Gatzoulis, C.; Tang, W. (Wen); Stoddart, W. J. (Bill) Editors: McDerby, M.; Lever, L. Sun, 01 Jan 2006 00:00:00 GMT http://hdl.handle.net/10149/250353 2006-01-01T00:00:00Z http://hdl.handle.net/10149/250372 Title: Learning by experience - autonomous virtual character behavioural animation Authors: Wan, T. R. (Tao Ruan); Tang, W. (Wen) Editors: Earnshaw, R. (Rae); Vince, J. (John) Tue, 01 Jan 2002 00:00:00 GMT http://hdl.handle.net/10149/250372 2002-01-01T00:00:00Z http://hdl.handle.net/10149/250352 Title: Fuzzy reinforcement learning for an evolving virtual servant robot Authors: Gatzoulis, C.; Tang, W. (Wen); Wan, T. R. (Tao Ruan) Abstract: This work presents our research in the application of reinforcement learning algorithms for the generation of autonomous intelligent virtual robots, that can learn and enhance their task performance in assisting humans in housekeeping. For the control system architecture of the virtual agents, two algorithms, based on Watkins' Q(λ) learning and the zeroth-level classifier system (ZLCS), are incorporated with fuzzy inference systems(FlS). Performance of these algorithms is evaluated and compared. A 3D application of a virtual robot whose task is to interact with virtual humans and offer optimal services on everyday in-house needs is designed and implemented. The learning systems are incorporated in the decision-making process of the virtual robot servant to allow itself to understand and evaluate the fuzzy value requirements and enhance its performance. Sat, 01 Jan 2005 00:00:00 GMT http://hdl.handle.net/10149/250352 2005-01-01T00:00:00Z