At present, unmanned vehicles (UV) to provide accurate navigation during motion depends on GPS. The search and study for the alternative methods of UV localization is demand to the implementation of smart city concepts, because in real-world conditions the GPS signal may either be absent, or its accuracy may be insufficient to trajectory following and perform maneuvers. Control systems based on network models of local positioning partially solves the problem of a safety motion. The paper emphasizes three main categories of UV software systems providing correspondingly, collection and processing data, planning, and control, as well as an approach to the architecture of decision making for UV, based on networking and computational multilevel analytics. To increase the UV safety level in a smart city, one proposes to use a safety management system based on the factor analysis and risks calculation techniques. In part of the collision avoidance to rise UV safety, network model of local positioning is proposed.