RESUMEN
In the development of autonomous driving technology, 5G-NR vehicle-to-everything (V2X) technology is a key technology that enhances safety and enables effective management of traffic information. Road-side units (RSUs) in 5G-NR V2X provide nearby vehicles with information and exchange traffic, and safety information with future autonomous vehicles, enhancing traffic safety and efficiency. This paper proposes a communication system for vehicle networks based on a 5G cellular network with RSUs consisting of the base station (BS) and user equipment (UE), and validates the system performance when providing services from different RSUs. The proposed approach maximizes the utilization of the entire network and ensures the reliability of V2I/V2N links between vehicles and each RSU. It also minimizes the shadowing area in the 5G-NR V2X environment, and maximizes the average throughput of vehicles through collaborative access between BS- and UE-type RSUs. The paper applies various resource management techniques, such as dynamic inter-cell interference coordination (ICIC), coordinated scheduling coordinated multi-point (CS-CoMP), cell range extension (CRE), and 3D beamforming, to achieve high reliability requirements. Simulation results demonstrate improved performance in outage probability, reduced shadowing area, and increased reliability through decreased interference and increased average throughput when collaborating with BS- and UE-type RSUs simultaneously.
RESUMEN
The accelerated growth of 5G technology has facilitated substantial progress in the realm of vehicle-to-everything (V2X) communications. Consequently, achieving optimal network performance and addressing congestion-related challenges have become paramount. This research proposes a unique hybrid power and rate control management strategy for distributed congestion control (HPR-DCC) focusing on 5G-NR-V2X sidelink communications. The primary objective of this strategy is to enhance network performance while simultaneously preventing congestion. By implementing the HPR-DCC strategy, a more fine-grained and adaptive control over the transmit power and transmission rate can be achieved. This enables efficient control by dynamically adjusting transmission parameters based on the network conditions. This study outlines the system model and methodology used to develop the HPR-DCC algorithm and investigates its characteristics of stability and convergence. Simulation results indicate that the proposed method effectively controls the maximum CBR value at 64% during high congestion scenarios, which leads to a 6% performance improvement over the conventional DCC approach. Furthermore, this approach enhances the signal reception range by 20 m, while maintaining the 90% packet reception ratio (PRR). The proposed HPR-DCC contributes to optimizing the quality and reliability of 5G-NR-V2X sidelink communication and holds great promise for advancing V2X applications in intelligent transportation systems.
RESUMEN
Lane detection is a significant technology for autonomous driving. In recent years, a number of lane detection methods have been proposed. However, the performance of fast and slim methods is not satisfactory in sophisticated scenarios and some robust methods are not fast enough. Consequently, we proposed a fast and robust lane detection method by combining a semantic segmentation network and an optical flow estimation network. Specifically, the whole research was divided into three parts: lane segmentation, lane discrimination, and mapping. In terms of lane segmentation, a robust semantic segmentation network was proposed to segment key frames and a fast and slim optical flow estimation network was used to track non-key frames. In the second part, density-based spatial clustering of applications with noise (DBSCAN) was adopted to discriminate lanes. Ultimately, we proposed a mapping method to map lane pixels from pixel coordinate system to camera coordinate system and fit lane curves in the camera coordinate system that are able to provide feedback for autonomous driving. Experimental results verified that the proposed method can speed up robust semantic segmentation network by three times at most and the accuracy fell 2% at most. In the best of circumstances, the result of the lane curve verified that the feedback error was 3%.
RESUMEN
The goal of automatic parking system is to accomplish the vehicle parking to the specified space automatically. It mainly includes parking space recognition, parking space matching, and trajectory generation. It has been developed enormously, but it is still a challenging work due to parking space recognition error and trajectory generation for vehicle nonparallel initial state with parking space. In this study, the authors propose multi-sensor information ensemble for parking space recognition and adaptive trajectory generation method, which is also robust to vehicle nonparallel initial state. Both simulation and real vehicle experiments are conducted to prove that the proposed method can improve the automatic parking system performance.