Unknown Environment For Mobile Robot Self-localization Algorithm

Map building not only is very important to accomplish autonomous navigation and other complex intelligent tasks, but also embodies perception ability and intelligence of robots. Mobile robot localization is an important topic in the intelligent robot domain. It includes sensory techniques and localization algorithms. An advantage of global localization is that the localization algorithm provides a means of estimating robot position under global uncertainty.This thesis focuses on the self-localization algorithm for mobile robots in unknown environment, and mainly on the map building and the localization approaches. The research topics include approaches of Temporal Local Occupancy Grids (TLOG), type of landmark recognize during map building and modified algorithm of Monte Carlo localization.This thesis based on probability grid approach's research. A modified algorithm via combining Temporal Local Occupancy Grids (TLOG) method is proposed in this thesis. New algorithm heightens map's precision.However, in a symmetrical environment a robot using distance detector cannot find its position by means of Monte Carlo localization alone. A modified algorithm via using an angle Gaussian distribution method is proposed in this thesis to solve this problem. And enrich sampling approach via using genetic methods crossover, mutation is proposed in this thesis. New approach heightens robot's self-localization precision and robust.The thesis includes five chapters. In the first chapter, the background of the project, domestic and international the latest progress. The second chapter Some key techniques are analyzed in detail, such as map representation, localization and environment feature-extraction. At the same time, some typical research methods are introduced. The third chapter based on probability grid approach's research. A modified algorithm via combining Temporal Local Occupancy Grids (TLOG) method is proposed in this thesis. New algorithm heightens map's precision. The forth chapter based on Markov approach's research. Modified algorithm is proposed based on MCL. Chapter five is the conclusion of the whole thesis.