The integration of large language models (LLMs) with mobile edge computing (MEC) systems presents a novel approach to enhancing vehicle-to-everything (V2X) connected autonomous driving. This study aims to address the prevalent challenges in multi-model sensor data fusion, such as latency, privacy preservation, and the need for dynamic adaptation to evolving environmental conditions, by leveraging real-time data from LiDAR sensors. We propose an LLM-based framework to improve V2X driving assistance systems’ operational efficiency, safety, and reliability, where pictures and image recognition work as integrated data from multiple sensors to train various vehicle and lane detection models. Based on the benefits of federated learning, i.e., distributed at each MEC server and optimising models accordingly, these training models can avoid the data privacy issue in V2X driving assistance implementation. The application of generated test data significantly improves the success rate of the lane detection feature and pedestrian detection, by 95% and 85%, respectively. The experiment results demonstrate that our proposed framework is effective and feasible.

Normal Distribution Priority (NDP) algorithm is a path-planning strategy for unmanned systems navigating complex environments. NDP efficiently circumvents obstacles and navigates through constricted spaces while optimizing energy use. The algorithm consists of two stages: waypoint expansion and energy optimization. First, it selects optimal waypoints using a normal distribution-based weighting mechanism to create a secure route. Then, it fine-tunes the path to minimize energy consumption. Dynamic programming optimizes the process to ensure efficiency. Comparative analyses with RRT* and PSO algorithms demonstrate NDP’s advantages in obstacle negotiation, time efficiency, and path refinement, particularly in static environments. Experimental validations confirm the algorithm’s adaptability and effectiveness for complex path planning.

Autonomous driving has a significant impact on the strategic direction of the future development of the automotive industry. Most of the theoretical teaching content of vehicle engineering is still based on traditional vehicle mechanical engineering. There is a certain lack of articulation with the theory of automobile industries frontier development such as autonomous driving vehicle technology. Moreover, the teaching of automated driving technology is multidisciplinary as well as having very strong practical needs, but lacking of sufficient practical teaching to engage students. This paper focuses on the promotion of practical teaching methods for undergraduate student in the field of automated driving through participation in competitions, such as China National College Student Smart Car Competition, which includes practical teaching and learning exploration processes and methods, building a cross-disciplinary curriculum and training programme, and finally student takes the training tasks. By encouraging student to actively participate in disciplinary competitions, it fosters student enthusiasm for exploring multidisciplinary theoretical knowledge in automated driving technology and improves their practical hands-on skills. In additional, it cultivates student sense of teamwork as well as the active learning attitude of pioneering and innovation. A diversified interdisciplinary and cross-practical competence evaluation system is also proposed in this project, which not only promotes the student sense of participation in practical teaching, but also improve the teacher teaching enthusiasm.

Temperature is a key factor affecting the safety of the Lithium-ion (Li-ion) battery. Therefore, real-time thermal fault diagnosis is becoming more and more prominent, as battery faults can lead to local overheating and thermal runaway in severe cases. This article proposes a Chebyshev–Galerkin-based thermal fault detection and localization framework for the pouch-type Li-ion battery under limited sensing. First, the Chebyshev function is used to construct the spatial basis functions with global and orthonormal properties. Under the time–space (T-S) separation framework, the time coefficients can be derived through the Galerkin method using six sensors. Then, by decomposing the time coefficients using the independent component analysis, the temporal and spatial reference statistics can be formed for real-time fault detection. Finally, considering the detected fault snapshots, the thermal fault location can be identified by finding the maximum contributed position through T-S synthesis. Simulations and experiments demonstrate the effectiveness of the proposed method.

Autonomous underwater vehicles (AUVs) are increasingly used in marine studies, military applications, and undersea exploration. However, the battery performance affects AUVs range. In this paper, a framework of wireless AUVs energy sharing system is proposed which can do rapidly energy replenishment for AUVs. The path planning is a crucial aspect in AUVs energy sharing and automation, which requires to generate trajectories to specified goals. This article mainly focuses on avoiding irregular obstacles efficiently and narrow area passing ability at underwater environment based on Rapidly-exploring Random Trees Star (RRT*) and Particle Swarm Optimisation (PSO). The comparison and analysis of the two algorithms through the simulation results in the random obstacle environment and the irregular obstacle environment are provided in the finally.

Stanley algorithm is a classical algorithm in automatic driving path tracking algorithm, which has the advantages of low computational complexity and good tracking effect. However, the tracking accuracy of the traditional Stanley algorithm is limited by the gain parameters and the gain coefficients cannot be dynamically adjusted according to the road conditions. To improve the tracking accuracy and driving stability, an adaptive Stanley control algorithm based on DWA (DWA-Stanley) is proposed, which is used to sampling the velocity vector space and selecting the evaluation function, the vehicle motion planning is based on the best set of velocity values. In this paper, the DWA-Stanley algorithm is validated based on three different driving speeds. Simulation results show that an racecar using the DWA-Stanley algorithm has higher tracking accuracy and smoothness than a conventional Stanley.

Path tracking is an important part of autonomous vehicles. Stanley algorithm is widely used in path tracking control of front wheel steering vehicles. The traditional Stanley algorithm calculates the front wheel angle according to the relative geometric relationship between the vehicle pose and the reference path point, which depends on the nearest reference path point. It is suitable for the low-speed and small change in curvature of reference paths. In order to improve the tracking accuracy and stability of Stanley algorithm, a model predictive control path tracking algorithm based on adaptive Stanley is proposed, which considers the adaptive change of preview distance and vehicle dynamics. The comparative simulation analysis of the proposed control strategy and the traditional Stanley control shows that the model predictive control path tracking algorithm based on adaptive Stanley can maintain high trajectory tracking accuracy and vehicle stability at high speed.

Vehicle to vehicle (V2V) charging system had been present which can work together with plug-in EVs charging or operate independently. V2V charging technology can effectively solve the problem of a limited number of plug-in stations and the exhaustion of EVs during the journey. Wireless power transfer (WPT) technology has become a priority technology for V2V charging due to its convenience. This paper proposes an angular offset analysis in wireless V2V system and compares the effects of three transmitter coil structures on system efficiency. The CST simulation results show that the H-field of the two-coil (angle) transmitter structure is higher than the other two benchmark structures. Meanwhile, the hardware implementation results show that when the resonant coils have an angular offset, two-coil (angle) transmitter structure can effectively improve the system efficiency compared to the other two benchmark structures.

The slow development of energy storage technology combined with a limited number of plug-in charging stations negatively affects people's desire to purchase pure battery electric vehicles. A new wireless vehicle-to-vehicle charging technology structure is proposed, which can function with plug-in electric vehicles or operate independently. With a limited number of charging stations this technology can be used to increase charging opportunities through vehicle-to-vehicle (V2V) charging. V2V charging requires a number of technical challenges to be overcome, including the angular offset of the wireless power transfer resonant coils. The mutual inductance between two resonant coils is a key parameter for high power and efficient transfer of power. This paper presents the theory of angular offset multi-turn coil design.

With the development of power electronic converters, size reducing and reliability extending are desired. For modern converter that utilises inductors or transformers, the dimensions of magnetic components are commonly inversely proportional to its switching frequency. With the increase of switching frequency, higher dv/dt may cause miss-triggering faults and unstable turn-off. Those issues can be relieved by applying a negative bias to conduct the turn-off. However, a separate DC-DC converter is normally required to generate this negative voltage. In this paper, a novel self-driven negative bias generator for high-side switch is introduced. The novel gate driver can provide bipolar gate driving capability without the need for a separate negative voltage supply. A prototype converter has been built and verified that the proposed bipolar gate driver could effectively generates the required negative voltage for power semiconductor driving without using a charge pump or switching converter.

Wireless power transfer (WPT) could revolutionize global transportation and accelerate growth in the Electric Vehicle (EV) market, offering an attractive alternative to cabled charging. Coil misalignment is inevitable due to driver parking behaviour and has a detrimental effect on power transfer efficiency (PTE). This paper proposes a novel coil design and adaptive hardware to improve PTE in magnetic resonant coupling WPT and mitigate coil misalignment, a crucial roadblock in its acceptance. The new design was verified using ADS, providing a good match to theoretical analysis. Custom designed receiver and transmitter circuitry was used to simulate vehicle and parking bay conditions and obtain PTE data in a small-scale setup. Experimental results showed that PTE can be improved by 30% at the array's centre, and an impressive 90% when misaligned by 3/4 of the arrays radius. The proposed novel coil array achieves overall higher PTE compared to the benchmark single coil design.

Wireless power transfer (WPT) technologies have been widely used in many areas, e.g., the charging of electric toothbrush, mobile phones, and electric vehicles. This paper introduces fundamental principles of three WPT technologies, i.e., inductive coupling-based WPT, magnetic resonant coupling-based WPT, and electromagnetic radiation-based WPT, together with discussions of their strengths and weaknesses. Main research themes are then presented, i.e., improving the transmission efficiency and distance, and designing multiple transmitters/receivers. The state-of-the-art techniques are reviewed and categorised. Several WPT applications are described. Open research challenges are then presented with a brief discussion of potential roadmap.