Can robots learn to see

Abstract Since the late 1960s autonomous robots have been the subject of worldwide research efforts. Various techniques exist that enable mobile robots to navigate robustly within their environments. Some systems are commercially available, most of them for transport and floor-cleaning applications. However, in general they are not truly autonomous, as they require human aid to build appropriate environment models, e.g. navigation maps, which they need for planning. But even high-end research robots normally need help to configure and adjust their sensors, e.g. vision systems where the user has to tune lots of parameters before the robot can ‘see’ in the given environment. Real service robots will have to to do this autonomously, as no helping scientist will be available. This paper presents a first step into this direction. It shows how a useful, self-learning vision system can be constructed, and that such a system is able to supply the robot with the information required to ‘survive’ in complex everyday environments.