Tight integration of satellite and strapdown inertial navigation systems is used for automo tive vehicles and complicated by the necessity to design adequate models of the object of research. A universal stochastic model adequately reflecting the processes of arbitrary motion of a ground vehicle is synthesized in a canonical form. The model can be used for realization of tightly coupled inertial satellite navigation systems. The results of simulation modelling are given, which confirm the effi ciency of the synthesized model.

No abstract

Abstract. Our team has developed a neural network for road recognition on our digital twin, aimed at enhancing transportation-related applications. The neural network is trained on large datasets of road images and utilizes various deep learning architectures and techniques to improve its accuracy and reliability. The embedded neural network can recognize different road features, such as lane markings, road signs, and obstacles, and can identify the location and direction of the road. The integration of this neural network in our digital twin can help optimize transportation-related operations, reduce accidents, and improve overall traffic flow. The developed neural network architecture and training methodology, as well as its performance evaluation on various datasets, are presented in this paper. Additionally, the paper discusses the future directions for research in this area and the potential of the developed neural network for other applications in the digital twin domain.

The problem of covering a set by a family of subsets (the set covering problem --SCP) is relevant in many scientific applications. A natural generalization of SCP is the fuzzy set covering problem FSCP. This generalization achieves new levels of application of formal models and new limits of modeling adequacy.