The integration of advanced image analysis using artificial intelligence (AI) is pivotal for the evolution of autonomous vehicles (AVs). This article provides a thorough review of the most significant datasets and latest state-of-the-art AI solutions employed in image analysis for AVs. Datasets such as Cityscapes, NuScenes, CARLA, and Talk2Car form the benchmarks for training and evaluating different AI models, with unique characteristics catering to various aspects of autonomous driving. Key AI methodologies, including Convolutional Neural Networks (CNNs), Transformer models, Generative Adversarial Networks (GANs), and Vision Language Models (VLMs), are discussed. The article also presents a comparative analysis of various AI techniques in real-world scenarios, focusing on semantic image segmentation, 3D object detection, vehicle control in virtual environments, and vehicle interaction using natural language. Simultaneously, the roles of multisensor datasets and simulation platforms like AirSim, TORCS, and SUMMIT in enriching the training data and testing environments for AVs are highlighted. By synthesizing information on datasets, AI solutions, and comparative performance evaluations, this article serves as a crucial resource for researchers, developers, and industry stakeholders, offering a clear view of the current landscape and future directions in autonomous vehicle image analysis technologies.

Non-integer-order systems are used to model diffusion in conductive parts of electrical machines as they lead to more compact knowledge models and also to improve their precision. In this paper, a linear half-order impedance model of a ferromagnetic sheet deduced from the diffusion of magnetic field is briefly introduced. Then, from physical considerations and finite-element simulation, the nonlinear half-order impedance model of a ferromagnetic sheet is proposed, taking into account both saturation and diffusion effects. Next, it has been proved that this model can be successfully included in the equivalent circuits of a synchronous machine (SM), taking into account eddy currents in massive parts of the rotor or damper bars and of small-signal saturation. The new SM equivalent circuit is validated by stand-still frequency response tests performed on the solid salient-pole SM of 125 kVA for variable field excitation conditions. An example of the SM transfer function computation in relation to different magnetization levels indicates the usefulness of this modeling approach for robust control issues.

The article presents the Power Hardware-In-the-Loop (PHIL) dynamic model of a synchronous generator of 125 kVA for autonomous power generation system analysis. This type of system is typically composed of electrical energy sources in the form of several diesel generator units with synchronous machines, the main distribution switchboard and different loads. In modern power distribution systems, the proposed power management strategies are typically aimed at the minimization of fuel consumption by maintaining the operation of diesel generator units at peak efficiency. In order to design and test such a system in conditions as close as possible to the real operating conditions, without constructing an actual power distribution system, a PHIL model in the form of a power inverter that emulates the behaviour of a real synchronous generator is proposed. The PHIL model was prepared in the MATLAB/Simulink environment, compiled to the C language and fed into a 150 kVA bidirectional DC/AC commercial-grade converter driven by a HIL real-time simulation control unit. Experimental research was performed in the LINTE${}^2$ laboratory of the Gdańsk University of Technology (Poland), where the PHIL emulator was developed. The proposed model was validated by comparing the output voltages and currents as well as an excitation current with the measurements performed on the 125 kVA synchronous generator. The obtained results proved satisfactory compliance of the PHIL model with its real counterpart.

The article presents design and construction of the light two-wheeled vehicle powered by the brushless DC motor of 3 kW. The construction of the vehicle is based on a steel frame similar to the classical bicycle frame. The vehicle has been additionally equipped with pedals as an alternative driving source as well as with the standard motorcycle equipment, i.e. lamps, breaking light, horn, front disc brake, etc. The prime power source which is the BLDC motor has been installed in the rear wheel hub and is powered by a pack of 220 lithiumion power cells of 2600 mAh each. The nominal parameters of the designed power pack is 72 V and 27.5 Ah of capacity. The motor controller which can be powered by the voltage from 36 V to 95 V can deliver up to 80 A of current. It enables regenerative braking which increases an overall range of the vehicle. The article discusses also the problem of classification of such construction according to the Polish law described in the Act on the Law of Road Traffic as well as in the Regulation of the Minister of Infrastructure of 31 December 2002 on the technical conditions of vehicles and the scope of their necessary equipment. Finally, the designed construction has been tested on the MAHA LPS 3000 chassis dynamometer in order to measure mechanical and electrical parameters like maximal electric power of the motor, maximal mechanical power on the wheel, motor torque, maximal rotational speed, energy consumption, windings temperature reached, etc. These quantities will serve to further development of the designed construction.

The integration of advanced image analysis using artificial intelligence (AI) is pivotal for the evolution of autonomous vehicles (AVs). This article provides a thorough review of the most significant datasets and the latest state-of-the-art AI solutions employed in image analysis for AVs. Datasets such as Cityscapes, NuScenes, and CARLA form the benchmarks for training and evaluating different AI models, with unique characteristics catering to various aspects of autonomous driving. Key AI methodologies, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Transformer models, and Generative Adversarial Networks (GANs), are discussed. The article also presents a comparative analysis of various AI techniques in real-world scenarios, focusing on semantic image segmentation, 3D object detection, and vehicle control in virtual environments. Simultaneously, the role of multisensor datasets and simulation platforms like AirSim, TORCS, and SUMMIT in enriching the training data and testing environments for AVs is highlighted. By synthesizing information on datasets, AI solutions, and comparative performance evaluations, the article serves as a crucial resource for researchers, developers, and industry stakeholders. Offering a clear view of the current landscape and future directions in autonomous vehicle image analysis technologies.

Non integer order systems are used to model diffusion in conductive parts of electrical machines as they lead to more compact and knowledge models but also to improve their precision. Nevertheless, non integer order models have been established under linear conditions. It is than interesting to study the influence of saturation on such model parameters. In this article, a linear half-order impedance model of a ferromagnetic sheet deduced from the diffusion of the magnetic field is introduced. Then, a non linear half-order impedance model of the sheet is proposed. It is finally validated by performing 3D finite element simulations and experimentally verified on a 3 kVA saturated synchronous machine.