Volume 121, Nº 1 (2024): THEMED SECTION: FUNDAMENTAL PROBLEMS OF MANAGING UNMANNED VEHICLES IN A SMART CITY

This paper studies the possibilities of optimizing the main characteristics of the developed intelligent control system for unmanned ground vehicles with the use of genetic algorithms. Authors presented the software architecture designed on the basis of the developed simulation model of the behaviour of unmanned ground vehicles (UGVs) interacting with other road users such as manned ground vehicles (MGVs), pedestrians, etc. A two-objective optimization problem was formulated and solved, the objective functions of which are the output traffic flow and the number of potential accidents with a participation of UGVs. The Monte Carlo experiments were performed to confirm the sensitivity of the objective functions’ values to the control parameters of the model under various configurations of the street road network. The Pareto fronts are computed with the use of the previously created real-coded genetic optimization algorithms. It allows choosing the best trade-offs that provide the most preferable operating modes of the intelligent transportation system under various configurations of digital road networks (DRNs).

Vigilance decrement during monotonous work was studied using driving simulator. The objectives of the study were to evaluate psychophysiological predictors of vigilance decrement and to test two noninvasive techniques to reduce sleepiness: vibromassage chair cover and peppermint essential oil against the background of chronic sleep deprivation.
Eighteen healthy subjects with partial sleep deprivation participated in the study. Facial videotape, electroencephalogram (EEG), electrocardiogram (ECG) and cutaneous galvanic response (CGR) were recorded. Subjects were tested for sleepiness, general well-being, and reaction time.
Based on the test results, the subjects were in a state of chronic sleep deprivation and chronic stress. On average, they made 2.2 (0 to 7) errors per experiment. About 20% of the subjects’ errors were estimated to be caused by distraction rather than by falling asleep. Conclusions were drawn about the dependence of the level of attention and sleepiness on several factors, and the need for further research. Based on the experimental data, a list of recommendations for the design of driver condition monitoring systems was developed.

In this paper we propose a group of computer models to evaluate the system efficiency for detecting and countering unmanned vehicles in a smart city. The unmanned vehicles mean autonomous vehicles and unmanned aerial vehicles. We developed a simplified model of a heterogeneous traffic flow consisting of unmanned and human-controlled vehicles. The model allows one to study the process of intercepting an autonomous vehicle control of which has been intercepted. We created a simulation model of a system for detecting and countering the attack of a group of unmanned aerial vehicles as part of the study of the processes of countering unmanned aerial vehicles. Also, we solved the problem of intercepting a group of unmanned aerial vehicles by another group (swarm) of unmanned aerial vehicles for the first time in a threedimensional setting.

The paper discusses the concept of building an integrated flight safety system for unmanned aerial vehicles (UAVs) in a single smart city sky, including the designing of the operational safety methods, minimizing the risks associated with equipment failures; functional safety methods, eliminating the risks associated with collisions; psychophysiological safety methods, taking into account the control of the vehicle based on the characteristics of the human operator. The methods of operational and functional safety are based on a unified approach for modelfree processing of information on the input and output signals of the UAV’s flight control system. The realization of this approach will allow, first of all, scaling flight safety systems to different classes of aircrafts without the need to create complex mathematical models of each object separately.

Methods for holographic processing of noise signals have been developed for the detection and localization of small-sized underwater unmanned vehicles (UVs) with a low level of noise emission. A technique has been proposed for using autonomous uninhabited underwater vehicles (AUVs) with small-sized vector-scalar receiver (VSR) antennas on board to monitor the underwater environment. The appearances of the AUV-transport and AUVcarrier with a small-sized VSR antenna were created. Computational and full-scale experiments were performed, and holographic processing of experimental data was carried out. A new concept for constructing a robotic system for monitoring the underwater environment based on holographic processing is proposed. Prospects for the development of holographic processing for hydroacoustic signals are outlined.