Autonomous braking through vehicle precise decision-making and control to reduce accidents is a key issue, especially in the early diffusion phase of autonomous vehicle development. This paper proposes a deep reinforcement learning (DRL)-based autonomous braking decision-making strategy in an emergency situation. Three key influencing factors, including efficiency, accuracy and passengers' comfort, are fully considered and satisfied by the proposed strategy. First, the vehicle lane-changing process and the braking process are analyzed in detail, which include the critical factors in the design of the autonomous braking strategy. Second, we propose a DRL process that determines the optimal strategy for autonomous braking. Particularly, a multi-objective reward function is designed, which can compromise the rewards achieved of different brake moments, the degree of the accident, and the comfort of the passenger. Third, a typical actor-critic (AC) algorithm named deep deterministic policy gradient (DDPG) is adopted for solving the autonomous braking problem, which can improve the efficiency of the optimal strategy and be stable in continuous control tasks. Once the strategy is well trained, the vehicle can automatically take optimal braking behavior in an emergency to improve driving safety. Extensive simulations validate the effectiveness and efficiency of our proposal in terms of learning effectiveness, decision-making accuracy and driving safety.

Accurately discovering hazards and issuing appropriate warnings to drivers in advance or performing autonomous control is the core of the Collision Avoidance (CA) system used to solve traffic safety problems. More comprehensive environmental awareness, diversified communication technologies, and autonomous control can make the CA system more accurate and effective, thereby improving driving safety. In addition, the assistance of Artificial Intelligence (AI) technology can make the CA system adapt to the environment and facilitate fast and accurate decisions. Considering the current lack of a thorough survey of driving safety with sensing, vehicular communications, and AI-based collision avoidance, in this paper, we survey existing researches for state-of-the-art data-driven CA techniques. Firstly, we discuss the major steps of CA and key research issues. For each step, we review the existing enabling techniques and research methods for CA in detail, including sensing and vehicular communication for safe driving, as well as CA algorithm design. Particularly, we present a comparison between the most common AI algorithms for different functions in the CA system. Testbeds and projects for CA are summarized next. Finally, several open challenges and future research directions are also outlined.

A fundamental issue of the vehicular digital twin (DT) is efficiently synchronizing the data between the DT and the vehicular user (VUE). In this paper, we consider the heterogeneous vehicular networks (HetVNets) in which a VUE can connect to the network through different networks. The HetVNets can improve the efficiency of communication by providing seamless connections. However, the uneven distribution of VUEs and the dynamics of HetVNets make the environment more complex. Therefore, we propose the network selection algorithm for data synchronization between VUEs and DTs in the HetVNets, where the behaviour between the VUEs is considered as a competition for wireless resources. A learning-based prediction model residing in the DT is developed where the DT can predict the waiting time of each relay and transmit the predicted results to the VUE for decision-making. We model the network selection problem as a potential game considering both the transmission time and the waiting time obtained from the prediction model and prove the existence of Nash equilibrium (NE). We analyze the performance of the proposed algorithm, and simulation results show that our approach can effectively find the optimal strategy while achieving a fast convergence speed and high-level performance compared to the baselines.

The digital transformation within the automotive industry is accelerating towards an era dominated by autonomous vehicles, with vehicle-to-everything (V2X) communications being a fundamental enabler for this advancement. As vehicular networks evolve to meet the complex demands of autonomous driving, traditional communication systems encounter limitations in bandwidth and data transfer rates. Millimeter-wave (mmWave) communication emerges as a pivotal solution, offering the extensive bandwidth required for the high data throughput and low latency essential in modern vehicular communications. However, challenges loom, with beam alignment in mmWave V2X becoming a time-consuming process and the mmWave’s blockage effect impeding consistent and reliable vehicular communication links. Therefore, the development of efficient, real-time, and robust beam alignment technology is crucial for mmWave V2X communication. In this paper, we present a comprehensive survey of beam alignment techniques in mmWave V2X communication. We explore various approaches including beam sweeping, angle of arrival (AoA)/angle of direction (AoD) estimation, black-box optimization, and side information. Subsequently, we introduce performance metrics for assessing beam alignment performance and compare the performance of four beam alignment methods under different metrics. Finally, we summarize the future research directions and challenges faced by beam alignment techniques in mmWave V2X communication, offering valuable insights for researchers in this field.

The complex traffic and road environment pose considerable challenges to the accuracy, timeliness, and adaptive ability of connected and autonomous vehicles (CAVs) in making driving decisions. This paper uses vehicle collaboration and integrates the adaptive learning capabilities of machine learning and the interpretation capabilities of expert systems (ESs) in a unified architecture to form a hybrid autonomous driving guidance system, which not only solves the “bottleneck” of knowledge acquisition during the construction of expert systems but also solves the “black box” phenomenon of machine learning in the decision-making process. First, an autonomous driving strategy based on deep reinforcement learning (DRL) is proposed for CAVs to make decisions and extract corresponding rules. Next, we design an ES knowledge base expansion method including rule extraction, rule sharing, and rule test. Particularly, vehicular blockchain is adopted to ensure user privacy and data security during the rule-sharing process. Third, hybrid autonomous driving guidance combining ES and machine learning is proposed for CAVs to make accurate and efficient decisions in different driving environments. Once the strategy is well trained, it can effectively guide CAVs to cope with the complex traffic environment. Extensive simulations validate the performance of our proposal in terms of decision-making accuracy, effectiveness, and safety.

This article explores the optimal offloading strategy in the Internet of Vehicles (IoVs), which is challenged by three issues. First, the resources of edge servers are shared by multiple vehicles, leading to random changes over time. Second, as a vehicle would drive across consecutive edge servers, the offloading strategy needs to consider the overall edge resources along the trip. Third, at each vehicle, the computing tasks arrive continuously when driving. This dictates the offloading strategy to consider not only the current status but also the futuristic computing tasks. To tackle these issues, we propose a digital twin (DT) network framework. A DT network maintains DTs in the cyber-space to synchronize the real-world activities of vehicles. Therefore, task offloading decisions can be benefited by combining both the global information aggregated from neighbor twins and historical information uploaded by vehicles. With comprehensive information, the optimal offloading strategy can be determined. We characterize the offloading problem as a Markov Decision Process (MDP) and develop an A3C-based decision-making algorithm, which can learn optimal offloading actions that minimize the long-term system costs. Extensive experiments demonstrate the performance of our proposal in terms of fast convergence and low system costs when compared with other approaches.