Wednesday 25th April 2001 (6 pm)
ABSTRACT
Future domestic robots will need to adapt to the special needs of their users and to their environment. Programming by natural language will be a key method enabling computer language-naive users to instruct their robots. Its main advantages over other learning methods are speed of acquisition and ability to build high level symbolic rules into the robot.
The presentation describes initial steps and considerations towards the design of a practical system in which users teach a vision-based robot how to navigate in a miniature town. Users will use unconstrained speech within a restricted domain-specific lexicon determined by analysing a corpus of route instructions. This is expected to maximise speech recognition performance. The robot knows a set of primitive navigation procedures that the user can refer to when giving route instructions. The presentation reports on the analysis of the corpus in terms of lexicon and primitive actions procedures. It then elaborates on the system-wide constraints imposed by the use of Instruction-Based Learning (IBL) and describes proposed solutions.
DR GUIDO BUGMANN was born in 1953 and has two children.
He studied Physics at the University of Geneva in Switzerland. In 1986 he completed a PhD on "Fabrication of photovoltaic solar cells with a-Si:H produced by anodic deposition in a DC plasma". He has then worked at the Swiss Federal Institute of Technology in Lausanne on the development of a measurement system using an ultra-sound beam and neural networks to measure the size of air bubbles in bacterial cultures.
In 1989 he joined the Fundamental Research Laboratories of NEC in Japan and modeled the function of biological
neurons in the visual system. In 1992 he joined Prof. John G.Taylor at King's College London to develop applications
of the pRAM neuron model and develop a theory of visual latencies. In 1993 he joined the group of Prof. Mike Denham
at the University of Plymouth (UK) where he develops vision-based navigation systems for robots, and investigates
biological planning and spatial memory. He supervises PhD students and teaches neural computation at B.Sc. and
M.Sc. level. Dr Bugmann has 3 patents and over 90 publications. He is a member of the Swiss Physical Society, The
Neuroscience Society and the British Machine Vision Association.
The Evening Lectures are free to both members and non-members of SGES.
For further information contact:
Dr. Chris Christodoulou, Department of Computer Science, Birkbeck College chris@dcs.bbk.ac.uk