Understanding sensory processing and its use in guiding behaviour. Building artificial visual systems. Applying work to collision avoidance in vehicles. Discovering circuitry for collision avoidance. Computational modelling. Reconsruction of fine ultrastructural details of sensory ciruitry
The principal conclusions of my recent research are that neurones responding selectively to objects moving in depth have a common receptive field organisation. Incorporating this organisation into an artificial network enabled the network to respond preferentially to approaching objects, regardless of the exact approach trajectory. This work has implications for artificial collision avoidance devices and the network is the first to track the rapidly expanding images of objects approaching on a collision course. A number of reports assessing the potential value of the neural network, based on the input organisation of the LGMD/DCMD neurones, for collision avoidance by autonomous guided vehicles have been published.
Currently I am part of a European Consortium consisting of an industrial partner: Volvo Car Corporation and two University partners Departments of Electronics (Seville ,Spain)and Analogical and Neural Computing Laboratory (ANCL), Computer and Automation, Reseach Institute of the Hungarian Academy of Sciences, Computer and (Budapest, Hungary). We are designing collision sensors based on the locust visual system for use on cars. Collision threat detection and avoidance defines a major Research and Development challenge for the automotive industry. Adaptive cruise-control systems incorporating some collision-avoidance features are offered today as pricey options on luxury cars. However, the performance of these systems is not always sufficient, and their cost is too high for wide use. Significant improvements are still needed for these systems to perform satisfactory and to become popular.
Future cruise-control systems will probably fuse data from different types of sensors, with optical images, and therefore vision, playing a significant role. However, present conventional approaches to vision, consisting of a camera that acquires the data and a separate digital processor that process it, are too slow for the most demanding tasks. New solutions are needed. Our EC funded project embraces advanced research and development activities focused on creating single-chip bio-inspired visual perception systems for automotive applications. These systems will be based on the outstanding performance of natural visual sensory-processing systems. As a central reference point, the project focuses on the integrated visual neuro-system for collision avoidance found in grasshoppers, which will be studied, modelled and emulated by means of sensory-processing chips in standard CMOS technologies. The resulting electronic systems will be able to operate correctly within the wide range of environmental conditions encountered in real-life automotive applications, and will meet the strict reliability standards of the car industry.
2003-2006 BBSRC 225K "The roles of the locust DCMD neurone in the control of behaviour"Co-investigator with Dr P Simmons
2003-2004 Joint Royal Society and Japan Society for the promotion of Science Fellowship 50K, 2003-2004
2002-2005 EU 5th Framework € 2,500K (509K to School of Biology) PI
2000-2003 GATSBY CHARITABLE FOUNDATION 60K Studentship plus support grant. PI
Relevance to collision avoidance in cars and other vehicles. I am part of a European Consortium consisting of an industrial partner: Volvo Car Corporation and and a two university partners National Centre for Microelectronics (Seville,Spain) and Centre for Cellular Neural Newtorks (Budapest, Hungary). We are designing a collision sensor based on the locust visual system for use on cars. Collision threat detection and avoidance defines a major Research and Development challenge for the automotive industry. The project brings together a multi-disciplinary team including mixed-signal microelectronic designers (IMSE-CNM), one automotive industry (VCC), neurobiologists (University of Newcastle upon Tyne)), and an opto-electronic information technology company (ANCL) to target the development of these new solutions.The EC funded project embraces advanced research and development activities focused on creating single-chip bio-inspired visual perception systems for automotive applications. I am the project leader for the current phase of the work.