Recently, there has been a rapidly emerging demand for localization technologies to provide various location-based services in indoor environments, such as smart buildings, smart factories, and parking lots, as well as outdoor environments. Ultra-wideband (UWB), an emerging wireless technology, provides opportunities for precise indoor positioning with sub-meter accuracy, much more accurate than WiFi or BLE-based techniques, thanks to its signal and communication characteristics. UWB technology has recently begun to be applied to personal devices such as smartphones and is expected to be used for indoor localization of personal devices. However, personal devices often cause signal problems because they are worn on human hands or bodies and move dynamically or are in a non-line-of-sight (NLoS) condition, such as pockets or bags. Therefore, these challenges in the dynamic environment of personal devices must be addressed to enable accurate indoor positioning services based on UWB. In this paper, we propose a novel UWB-based indoor positioning approach that significantly improves localization accuracy under dynamic personal device environments. Our proposed approach detects various NLoS conditions of personal environments by leveraging channel impulse response (CIR) and deep learning. Based on the detected NLoS conditions, the proposed approach adjusts the Kalman filter to adaptively estimate the position of the target UWB-based personal device. Specifically, the distance measurement errors by NLoS are minimized by applying weights determined by deep learning to the Kalman filter. Through experiments conducted in practical indoor environments, we have shown that our proposed approach considerably improves the accuracy compared to the traditional Kalman filter-based and trilateration approaches. According to our method of counting the number of points relative to ground truth, the proposed positioning system improved positioning accuracy significantly by 20.84% to 27.22% with an error tolerance of ±25 cm and by 7.78% to 22.78% with an error tolerance of ±50 cm, compared to the traditional approaches.

Lane changing systems have consistently received attention in the fields of vehicular communication and autonomous vehicles. In this paper, we propose a lane change system that combines deep reinforcement learning and vehicular communication. A host vehicle, trying to change lanes, receives the state information of the host vehicle and a remote vehicle that are both equipped with vehicular communication devices. A deep deterministic policy gradient learning algorithm in the host vehicle determines the high-level action of the host vehicle from the state information. The proposed system learns straight-line driving and collision avoidance actions without vehicle dynamics knowledge. Finally, we consider the update period for the state information from the host and remote vehicles.

Connected and automated vehicles (CAVs) have recently attracted a great deal of attention. Various studies have been conducted to improve vehicle and traffic safety through vehicle to vehicle (V2V) communication. In the field of CAVs, lane change research is considered a very challenging subject. This paper presents a cooperative lane change protocol, considering the impact of V2V communication delay. When creating a path for a lane change in the local path planning module, V2V communication delay occurs. Each vehicle was represented, in our study, by an oriented bounding box (OBB) to determine the risk of collision. We set up a highway driving simulation environment and verified the improved protocol by implementing a longitudinal and lateral controller.

Fifth-generation (5G) technology is rapidly spreading to vehicle-to-vehicle (V2V) communication, which requires high reliability, high data transmission rate, and low latency to meet service requirements through a new frequency band called millimeter wave (mmWave). However, mmWave bands are difficult to utilize in a dynamically changing vehicle environment because of the propagation attenuation against obstacles. Various studies are underway to predict the path loss in the mmWave band on roads with many obstacles. However, it is still challenging to accurately predict the path loss in various environments because the existing prediction models either generalize the path loss solely based on measurement data or only use specific parameters. Recently, investigations on artificial intelligence have been conducted using various techniques that are different from the existing heuristic methods. Following this trend, we propose a deep learning-based path loss prediction that considers obstacles on roads and weather conditions in V2V communication using mmWave. To consider the various environments affecting measurement, we constructed a realistic simulation environment and collected data that we used to train our deep learning models. Our proposed deep learning-based approach achieves accurate predictions for path loss.