AN ARCHITECTURE FOR DISTRIBUTED VISUAL MEMORY

The development of autonomous as well as situated robots is one of the great remaining challenges and involves a number of different scienti fic disciplines. In spite of recent dramatic progress, it remains wort hwhile to examine natural systems, because their abilities are still o ut of reach. Motivated by research work done in the fields of cognitiv e systems, visual perception, and psychology of memory we designed and implemented a memory architecture for visual tasks. Structural and fu nctional concepts of the memory architecture were modeled on the ones found in natural systems. We present an efficient implementation based on parallel programming techniques. The memory module is integrated i nto a distributed system for speech and image analysis, which is curre ntly developed in the Sonderforschungsbereich (SFB) 360, Situated Arti ficial Communicators, where a hybrid vision system combining neural an d semantic networks is used.