Large language model-related technologies have shown astonishing potential in tasks such as machine translation, text generation, logical reasoning, task planning, and multimodal alignment. Consequently, their applications have continuously expanded from natural language processing to computer vision, scientific computing, and other vertical industry fields. This rapid surge in research work in a short period poses significant challenges for researchers to comprehensively grasp the research dynamics, understand key technologies, and develop applications in the field. To address this, this paper provides a comprehensive review of research on large language models. First, it organizes and reviews the research background and current status, clarifying the definition of large language models in both Chinese and English communities. Second, it analyzes the mainstream infrastructure of large language models and briefly introduces the key technologies and optimization methods that support them. Then, it conducts a detailed review of the intersections between large language models and interdisciplinary technologies such as contrastive learning, knowledge enhancement, retrieval enhancement, hallucination dissolution, recommendation systems, reinforcement learning, multimodal large models, and agents, pointing out valuable research ideas. Finally, it organizes the deployment and industry applications of large language models, identifies the limitations and challenges they face, and provides an outlook on future research directions. Our review paper aims not only to provide systematic research but also to focus on the integration of large language models with interdisciplinary technologies, hoping to provide ideas and inspiration for researchers to carry out industry applications and the secondary development of large language models.

This paper addresses a collision avoidance problem for multiple unmanned aerial vehicles (UAVs) in the process of high-speed flight, thereby enabling UAV cooperative formation flight and effective mission completion. The main contribution is to propose a collision avoidance control algorithm for a multi-UAV system based on a bi-directional network connection structure. To effectively avoid collisions between UAVs and between UAVs and obstacles, the proposed consensus-based algorithm and a “leader-follower” control strategy are simultaneously applied for UAV formation control to ensure the convergence of the formation. Each of the UAVs has the same forward velocity and heading angle in the horizontal plane, and they maintain a constant relative distance in the vertical direction. This paper proposes a consensus-based collision avoidance algorithm for multiple UAVs based on an improved artificial potential field method. Simulation tests involving multiple UAVs were performed to validate the proposed control algorithm and to provide a reference for engineering applications.

Aimed at the problem that the unmanned aerial vehicle (UAV) close formation cannot maintain its desired formation shape due to the wind field disturbances, a novel distributed adaptive control approach is proposed to counteract the lateral and forward distance errors caused by uncertain wind field disturbances. Firstly, based on the ``leader-follower'' model, an adaptive control law is designed to accurately estimate the magnitude and direction of the wind in 3-D space. Then, the distance errors caused by uncertain wind field disturbances is counteracted by controlling UAV relative movement. Moreover, their velocity can keep constant to achieve the desired formation shape. Additionally, the signals of the closed-loop system are semi-globally practical finite-time stable (SGPFS). Finally, the simulation results show that the proposed adaptive control algorithm has good robustness, which provides a theoretical basis for engineering practice.

Aiming at a class of high-order strict feedback nonlinear multi-agent system (MAS) with communication constraints, a novel distributed adaptive back-stepping control method is proposed to cooperatively track the moving targets. Firstly, five agents are used as controlled objects, and all five agents form a “leader-follower” mode with a distributed control structure. Meanwhile, the leader's moving velocity is considered the forward velocity of the whole formation system, and remaining agents follow the leader's movement. Then, each agent tracks the desired formation with a time-varying reference trajectory, thereby achieving the consensus tracking purpose of multi-agent system. Moreover, the multi-agent formation system avoids obstacles with the optimal trajectory and maintains the desired formation movement. Finally, the simulation results show that the designed controller can achieve the lateral and horizontal tracking errors of the multi-agent system to converge quickly, and then keep the system asymptotically stable during tracking process.