Unmanned aerial vehicle (UAV) swarms, characterized by high mobility, low cost, flexible deployment, and distributed coordination, demonstrate disruptive potential and broad application prospects across military (e.g., reconnaissance, electronic warfare) and civilian domains (e.g., disaster rescue, environmental monitoring, smart cities). The core enabler for UAV swarms to function as a cohesive unit and unleash their systemic effectiveness lies in efficient communication and networking technologies. However, the inherent attributes of UAV swarms—highly dynamic and resource-constrained—combined with the complexity and adversarial nature of their operational environments, pose unique challenges: High-dynamic flight leads to spatio-temporal-frequency non-stationary channels and volatile topology changes, invalidating traditional quasi-stationary channel assumptions; Severe on-board resource constraints (energy, computation) create conflicts between physical-layer energy scheduling and network-layer routing overhead, highlighting bottlenecks in cross-layer optimization efficiency; As a typical cyber-physical system (CPS), communication delay directly impacts control loop stability, yet the deep coupling mechanisms among communication, computation, and control (C3) remain unclear, making task-driven dynamic resource adaptation difficult. Furthermore, demands for large-scale reliable networking, real-time high-speed transmission, intelligent communication, robust anti-jamming capabilities, cost-effectiveness, and evolutionary development, coupled with new requirements driven by 6G-enabled low-altitude economy applications (e.g., integrated sensing and communication (ISAC), ubiquitous coverage, deterministic networking, intrinsic security), underscore communication and networking technologies for UAV swarms as a critical and urgent field for breakthroughs, holding significant research importance and practical value.

Significant progress has been made in UAV swarm communication and networking, reflected in layered technological systems and intelligent empowerment:

• Physical layer transmission: Addressing high-dynamic channels, research focuses on novel waveforms. Orthogonal frequency division multiplexing (OFDM) is widely used for its multipath resistance and compatibility with MIMO, but suffers from high peak-to-average power ratio (PAPR) and out-of-band emission (OOBE) limitations under high Doppler. Orthogonal time frequency space (OTFS) modulation, operating in the delay-Doppler domain, effectively combats time-frequency doubly dispersive channels, though high detection complexity remains a challenge. Low-complexity detection algorithms (e.g., optimized Message Passing) and integration with non-orthogonal multiple access (NOMA) are key research areas. Affine frequency division multiplexing (AFDM), compatible with OFDM through parameter tuning and achieving full diversity in linear time-varying channels, attracts interest for its lower complexity demodulation. Integrated control and data transmission waveforms (e.g., DSSS based on SC-FDE) are designed to meet diverse service needs. ISAC waveforms (e.g.,, OTFS/AFDM) leverage channel characteristics for environmental parameter sensing without extra hardware, with optimization schemes for UAV coordination being a frontier. Anti-jamming techniques encompass waveform-level approaches (DSSS, FHSS, burst communication) and suppression techniques in frequency/time/space domains (e.g., millimeter-wave (mmWave) directional communication). MmWave, with its vast bandwidth and narrow beams, offers great potential for anti-jamming and high data rates, but requires solutions for robust beamforming and rapid node discovery.

• Data link and network layer technologies: To tackle high-dynamic topology, research concentrates on hybrid communication (omnidirectional/directional), efficient medium access control (MAC) protocol design, multi-dimensional resource (power, spectrum, trajectory) optimization scheduling, high-dynamic routing protocols, and heterogeneous swarm networking. Hybrid communication combines omnidirectional neighbor discovery with directional anti-jamming. Resource scheduling aims to resolve competition in large-scale networking. Routing protocols must adapt to 3D high-speed mobility for low-latency reliable transmission.

• Communication, computing and control fusion and joint optimization: Recognizing UAV swarms as CPS, this research explored the mapping between communication delay, computational load, and control precision (e.g., formation keeping, task allocation), seeking joint optimization methods for task-driven dynamic resource adaptation.

• Intelligent empowerment: An intelligent architecture integrating "Intent Understanding - Environment Adaptation - Resource Scheduling" was proposed, enabling autonomous perception, intelligent decision-making, and dynamic network reconfiguration, supporting the evolution from "mechanical linkage" to "autonomous collaboration." Intelligent collaborative schemes for lightweight and weak-connectivity environments were explored.

• Engineering applications: Focus areas include high-frequency band hardware optimization, lightweight antenna design, and modular communication chips/protocols to overcome size, weight, and power (SWAP) constraints and facilitate deployment.

• Network security: UAV swarm communication security and intelligent protection techniques were summarized to counter threats in complex electromagnetic environments.

Communication and networking technologies are pivotal for UAV swarms to achieve systemic collaborative effectiveness. This review systematically outlines the key technological challenges, research status, and development trends in this field. Current research has made significant strides in physical layer waveforms (e.g.,, OTFS/AFDM), ISAC, anti-jamming (notably mmWave), hybrid networking and resource scheduling at the data link and network layers, C3 fusion, and intelligent architectures. Looking ahead, UAV swarm communication and networking will be deeply integrated into future space-air-ground integrated networks (SAGIN):

• Network architecture: A unified, open, and scalable SAGIN architecture supporting diverse UAV roles (aerial base station, relay, terminal, and ad-hoc node) is essential.

• Key technologies: Priority areas include optimization and lightweighting of high-frequency (mmWave/THz) communication hardware, deep C3 coupling mechanisms and joint optimization frameworks, intelligent autonomous network management, and high-reliability low-latency transmission (e.g., 6G deterministic networking), and intrinsic security mechanisms.

• Intelligence trend: AI will further empower swarms, enabling more precise intent understanding, environmental perception, and resource scheduling, enhancing autonomous collaboration and survivability in complex scenarios.

• Application-driven evolution: The large-scale development of the low-altitude economy will spur new requirements for ISAC-enabled intrinsic perception, ubiquitous coverage, high-density access management, and stringent safety regulations, driving technological advancements. Future research must deepen foundational exploration (e.g., high-dynamic channel modeling, C3 coupling mechanisms), and break through core technologies (e.g.,, lightweight high-frequency hardware, intelligent resource scheduling), and strengthen standardization and engineering applications to underpin the widespread adoption of UAV swarms in future intelligent networked warfare and the low-altitude economy.

Unmanned aerial vehicle (UAV) ad hoc networks are increasingly vital for civilian and military applications due to their rapid deployment and collaborative capabilities. However, their dynamic nature and diverse quality of service (QoS) demands, especially for time-sensitive multi-priority services (e.g., command, control, payload), impose significant challenges on medium access control (MAC) protocols. The statistic priority-based multiple access (SPMA) protocol, distinguished by its priority differentiation and channel load statistics, is a promising candidate for UAV networks. A critical factor influencing SPMA performance, particularly end-to-end delay and transmission success rate, is the backoff mechanism. Existing SPMA backoff strategies predominantly rely on static function models (e.g.,, Binary Exponential Backoff- BEB, logarithmic functions) with limited optimization dimensions (often only priority). These static approaches are inadequate for adapting to the highly dynamic and heterogeneous environment of UAV ad hoc networks, characterized by fluctuating channel loads, varying priority thresholds, and stringent resource constraints. This necessitates the development of an intelligent backoff strategy that can dynamically learn optimal backoff times by comprehensively considering multiple factors, such as service priority, current channel load, and priority thresholds, to enhance network efficiency and meet diverse QoS requirements.

To address the limitations of static backoff models, this paper modeled the dynamic decision-making process of selecting backoff times in SPMA as a Markov decision process (MDP). An intelligent backoff strategy based on the double deep Q-network (DDQN) algorithm was proposed. The UAV node acts as the agent interacting with the network environment. The state space was designed to capture both the priority of the current data packet to be sent and the channel load statistics, including historical values to learn trends. The action space consisted of discrete backoff times within finite windows defined by the maximum validity periods of different priority services. A reward function was meticulously crafted to guide learning, incorporating: (1) a backoff result factor (+1 for success, -1 for failure upon re-checking conditions after backoff); (2) the priority of the service (emphasizing higher priority); (3) the difference between the priority threshold and the channel load at the end of the backoff period (promoting minimal, efficient backoff). By employing separate current and target Q-networks updated at different frequencies, the DDQN framework mitigated the overestimation issue common in DQN and enhanced stability. The agent selects actions (backoff times) using an epsilon-greedy policy, balancing exploration and exploitation. Training leverages experience replay for sample efficiency. Crucially, the "offline training, online deployment" paradigm was adopted, where the DDQN model was trained on a server, and the lightweight inference model was deployed on UAVs, minimizing onboard computational burden.

The performance of the proposed DDQN-based intelligent backoff strategy was rigorously evaluated through simulation using OPNET Modeler 14.5 for the SPMA protocol and Python for the ML components, incorporating dynamic elements such as node mobility and bursty traffic. Comparative analyses were conducted against traditional BEB and a logarithmic function-based backoff strategy under various traffic load scenarios. Key results demonstrate the superiority of the DDQN approach: (1) Significant delay reduction: The strategy achieves up to a 33.3% reduction in transmission delay for low-priority services compared to the benchmark strategies. (2) Improved success rate: It enhances the initial backoff success rate by up to 18%, indicating a higher probability of successful transmission immediately after the backoff period. (3) Enhanced adaptability: The strategy effectively improves the overall transmission success rate and demonstrates robust adaptability to variations in network scale (number of UAV nodes). These improvements are attributed to the DDQN agent's ability to learn complex, non-linear relationships between the state factors (priority, channel load) and the optimal backoff action, dynamically adjusting to network conditions far more effectively than static models.

This study successfully addresses the critical challenge of designing an efficient backoff mechanism for the SPMA protocol in dynamic UAV ad hoc networks. By formulating the backoff time selection as an MDP and leveraging the DDQN algorithm, we developed an intelligent backoff strategy that dynamically optimizes backoff times based on a comprehensive consideration of service priority, channel load statistics, and priority thresholds. The simulation results conclusively demonstrate that this strategy outperforms traditional BEB and function-based approaches, significantly reducing delay (especially for low-priority traffic), improving initial backoff success rates, and enhancing overall transmission reliability while adapting well to network size changes. The "offline training, online deployment" approach ensures practical feasibility on resource-constrained UAV platforms. This DDQN-driven intelligent backoff technology presents a promising solution for achieving low-latency and high-reliability MAC layer communication in mission-critical UAV operations, paving the way for more efficient and robust UAV ad hoc networks. Future work could explore decentralized training and robustness under extreme mobility or jamming.