Conclusion

Abstract

Learning map is one of the key problems in mobile robotics, since many applications require known spacial models. Robots that are able to acquire an accurate map of the environment on their own are regarded as fulfilling a major precondition of truly autonomous mobile vehicles. The autonomous map learning problem has several important aspects that need to be solved simultaneously in order to come up with accurate models. These problems are mapping, localization, and path planning. Additionally, most mapping approaches assume that the environment of the mobile robots is static and does not change over time. This assumption, however, is unrealistic since most places are populated by humans. Taking into account non-static aspects is therefore an desirable feature for mapping systems.