Sponsoring company. Foster and Partners (Architecture, planning and design)
Research area. Adaptive architecture
Research abstract. The design of architecture is the design of a highly complex, organised system. This research investigates the automation of various aspects of this process with the aid of machine learning and optimisation algorithms. The hypothesis is that knowledge gained through simulation of a system’s behaviour allows the computer to make the kinds of judgements or decisions that can be used to guide the design. Two situations are being studied: the manufacture of highly detailed space frame structures with specific load bearing or dynamic properties, and the planning of spaces to reflect given social relationships as quantified by space syntax techniques.
- 2003. An Evolutionary approach to microstructure optimisation of stereolithographic models
- 2004. Blurring the Boundaries between Actuator and Structure: Investigating the use of Stereolithography to build Adaptive Robots.
- 2004. Optimising Continuous Microstructures: A Comparison of Gradient-Based and Stochastic Methods.
- 2004. Creativity Through Embodiment: A computational model exemplified by microstructure design
- 2004. Modularity and Flexibility at the Small Scale: Evolving Continuous Material Variation with Stereolithography.
- 2006. A Transformed Architecture. In McQuaid M (Ed.) Extreme Textiles
|< Prev||Next >|
Siavash Haroun Mahdavi
Sponsoring company. BAe Systems - Aerospace and Defence
Research area. Adaptive robotics
Research abstract. This work deals with a robot where no domain knowledge is given at all. The genetic algorithms used to control these robots are deeply embodied within their environment. This embodiment means that a very simple genetic algorithm is able to control smart materials like shape memory alloys without any previous domain knowledge about them. The control and exploitation of smart materials is also extended to stereolithographic models. The final outcome of this research will be a robot that is made entirely out of smart materials. This robot will be able to perform a variety of tasks from locomotion, to damage recovery, and even optimising its shape to get the best reception.Read more
In the field of post-stroke rehabilitation, there appears to be growing interest in the use ofvirtual reality (VR)-based systems as adjunct technologies to standard therapeutic practices.The limitations and the potentials of this technology are not, however, generally wellunderstood. The present study thus seeks to determine the value of the technology withreference to end-user requirements by surveying and evaluating its application against avariety of parameters: user focus, clinical effectiveness, marketability and contextualmeaningfulness, etc. A key theme in the research considers how a technology developedinternationally might interface with care provision demands and cultures specific to the UnitedKingdom.
The barriers to innovation entry in this context are thus examined. Further practicalstudy has been conducted in the field with a small sample of post-stroke rehabilitation patients.The data garnered from these enquiries have informed a detailed system analysis, a strategyfor innovation and a broad theoretical discussion as to the effectiveness of the technology indelivering VR environments by which the patient can undertake ‘meaningful’ therapeuticactivities. The data reveal that there does appear to be clinical value in using this technology,yet establishing its maximal value necessitates greater integrity among clinicians andengineers, and the furthering of progressive channels for innovation by public healthadministrators.