A NEURAL ARCHITECTURE FOR VISUAL INFORMATION-PROCESSING

We report on the work done at the Institut fur Neuroinformatik in Boch um concerning the development of a neural architecture for the informa tion processing of autonomous visually guided systems acting in a natu ral environment. Since biological systems like our brain are superior to artificial systems in solving such a task, we use findings from neu rophysiology and -anatomy as well as psychophysics for defining proces sing principles and modules that have been implemented on our mobile p latform MARVIN. MARVIN is equipped with an active stereo camera system . Our final objective is to define a neural instruction set for early information processing in the sense of a perception for action approac h. From the biological paradigm we use principles like active vision, foveation, two-dimensional cortical layers, mapping, and discrete para metric representations in a task-oriented way to solve problems like o bstacle avoidance, path planning, scene recognition, tracking, and 3D perception. This paper has the character of an overview of the work do ne in this field at our institute. Most of the modules presented here were published either in conference proceedings or in journals which w ill be referenced for a more thorough discussion of each issue.