real-time systems

This paper investigates the impact of architectural scaling in YOLO-family neural object detectors on object detection performance in unmanned aerial vehicle (UAV) systems under CPU-only inference conditions without hardware acceleration. Standard nano and small model configurations are analyzed, along with an intermediate model obtained through controlled width scaling of the network. Experimental evaluation is conducted on an embedded Raspberry Pi 5 platform under fixed hardware and software conditions using ONNX Runtime, ensuring fair comparability of the models.

This paper presents an experimental study of communication latency in ESP-NOW wireless networks under different indoor conditions. A testbed consisting of three ESP32 devices (one master and two slave nodes) has been developed to evaluate one-way transmission delays without the use of a Wi-Fi access point. The slave nodes generate periodic sensor traffic and transmit data simultaneously, creating controlled network load conditions. A software-based time synchronization mechanism based on a message-exchange protocol has been implemented to estimate one-way latency.

Modern digital control systems make it possible to implement quite complex control strategy, the complexity of which is limited by the hardware capabilities, the available software and the implemented control algorithm. An important component of such an algorithm is the numerical method, which allows to discretize the control rule on the basis of a continuous prototype. Such application example is the classic PID controller, which has become the basis for the development of digital control systems.