Large AI models have been widely adopted in wireless communications for channel modeling, beamforming, and resource optimization. However, most existing efforts remain limited to single-modality inputs and channel-specific objec- tives, overlooking the broader potential of large foundation models for unified wireless sensing. To bridge this gap, we propose MMSense, a multi-modal, multi-task foundation model that jointly addresses channel-centric, environment-aware, and human-centered sensing. Our framework integrates image, radar, LiDAR, and textual data by transforming them into vision- compatible representations, enabling effective cross-modal align- ment within a unified feature space. A modality gating mecha- nism adaptively fuses these representations, while a vision-based large language model backbone enables unified feature align- ment and instruction-driven task adaptation. Furthermore, task- specific sequential attention and uncertainty-based loss weighting mechanisms enhance cross-task generalization. Experiments on real wireless scenario datasets show that our approach outper- forms both task-specific and large-model baselines, confirming its strong generalization across heterogeneous sensing tasks.

The Internet of Thing (IoT) devices play a vital role in collecting mission-critical and time-sensitive sensing data from remote areas, where traditional terrestrial networks are constrained by sparse infrastructures. However, resource-limited ground devices (GDs) in such scenarios often lack the ability to directly transmit essential information to distant data centers. To overcome this challenge, this paper proposes a Satellite-unmanned aerial vehicle (UAV)-assisted data collection framework, where the UAV is controlled by a remote control center via satellite relays. Aiming to maximize the energy efficiency (EE) of the UAV, we first design a reference trajectory to the UAV with given hovering positions. Subsequently, we optimize the power allocation for communication and state sensing strategies for trajectory tracking control, while guaranteeing control stability and communication reliability. These challenging problems are addressed using sequently an efficient algorithm, incorporating Deep Q-Network (DQN), closed-form derivations, and one-dimensional search method. Extensive numerical simulations and experimental validations are conducted to demonstrate the effectiveness of the proposed approach. Key findings point that the data size of collection has greater impacts than transmission power. Moreover, the results reveal the relationships among the communication, control and state sensing in terms of the EE.

Open Radio Access Network (O-RAN) supports heterogeneous service coexistence through functional splitting and open interfaces, enabling traffic steering via functional orchestration and resource scheduling. However, existing studies focus on known traffic patterns and lack the ability to anticipate dynamic service demands in advance. Isolated optimization of orchestration and scheduling fails to ensure End-to-End (E2E) latency. The varying time scales and vast solution space further complicate the joint optimization. To address this, we propose a traffic twin-enabled orchestration and scheduling multi-timescale joint optimization scheme. Explicitly, we design a spatiotemporal attention-assisted Time Series Generative Adversarial Network (TimeGAN) traffic twin model (STAG-TD) to capture unknown traffic patterns. Based on twin results, we formulate a joint optimization problem and design a dual-timescale algorithm framework, including propose a Task Decomposed Dueling Double Deep Q-Network (TD3QN) algorithm to handle large-timescale orchestration, and use a Penalty-based Particle Swarm Optimization (PPSO) algorithm to manage small-timescale scheduling. Our scheme achieves a predictive joint optimization to reduce the transmission latency of services. Extensive results show our scheme outperforms state-of-the-art methods, reducing E2E latency by over 39% and increasing throughput by over 14.9%. The highly consistent results between real and twin data also demonstrate the effectiveness of the traffic twin model.

The Digital Twin (DT) system has become a new paradigm to empower Unmanned Aerial Vehicles (UAV) networks for low-altitude applications, such as parcel delivery. However, due to high computing complexity, traditional DT technology might confront challenges to imitating highly dynamic UAVs in large-scale parcel delivery scenarios. It causes a negative influence on low-latency and high-accuracy delivery. To address the issue, we propose a terminal-edge cooperative multi-scale DT framework. It can perform a cooperative DT implementation with a cross-layer computing resource orchestration based on a multi-scale imitation manner. Explicitly, we propose a graph matching network based DT algorithm to run macro-scale DTs at the edge. It can assist edge UAVs in exploring feasible delivery associations among UAV groups and parcel clusters based on information on UAV topology and parcel destinations for a high successful delivery ratio. We then propose a Competitive and Cooperative Reinforcement Learning (CCRL) based DT algorithm to implement micro-scale DTs at the terminal. It can enable UAVs to implement low-latency delivery by optimizing delivery paths with low energy consumption. We demonstrate the effectiveness of the proposed framework with verifications under multiple metrics. The results show that our solution provides a real-time UAV delivery performance, with up to 94% successful delivery ratio, under a low system latency compared to the state-of-the-art solutions.

Unmanned Aerial Vehicles (UAVs) have been an attractive device to serve target tracking scenarios, such as hit- and-run tracking and border patrol. Nonetheless, it is difficult to implement real-time UAV topology optimization due to communication resources of UAVs and random moving speeds of targets. To address the problem, we propose a Digital Twins-assisted topology optimization framework (TopoDT). We formulate a UAV topology optimization model based on Lyapunov theory in the framework. The model is decoupled into two subproblems using our proposed TopoDT topology optimization algorithm. The DT model can allow UAVs to implement neighbor selection to construct and optimize small-scale local topologies for tracking low-speed moving targets. In addition, it allows UAVs to construct large-scale global topologies for tracking high-speed moving targets based on trajectory derivation. The system simulation results demonstrate that our solution reduces the end-to-end latency by 63.0% while decreasing the hop counts by 50% compared to state-of-the-art benchmarks.

Unmanned Aerial Vehicles-based Multiple Targets Tracking (UAV-MTT) has been mainstream in serving mission-critical scenarios for public safety, such as hit-and-run tracking and border patrol. Nonetheless, it is challenging to implement high-efficiency UAV topology control due to the variable moving speeds of targets and the limited sensing and communication resources of UAVs. To address the problem, we propose a terminal-edge cooperative Digital Twin (DT) framework for real-time and accurate MTT. Based on the DT technology, we achieve joint optimization of local and global UAV topologies to track targets with diverse speeds. Explicitly, we construct time-spatial DT models based on temporal and spatial information of targets and UAVs. The DT models can instruct UAVs to dynamically adjust position relations among one-hop neighbors for local topology optimization using our proposed Time Spatial Graph Learning based DT (TSGL-DT) algorithm. UAVs can use the optimization results to invite feasible neighbors to track low-speed moving targets. Our DT models can also allocate feasible UAVs to connect suitable local topologies for global topology optimization. It can achieve cooperative MTT to track high-speed moving targets. The experiment results demonstrate that our solution reduces the MTT latency by 41.2% while improving the successful tracking ratio delivery ratio by 15.6% on average compared to state-of-the-art benchmarks.

With the development of cyber-physical systems, Digital Twins (DT)-powered network autonomy is emerging to embrace the fifth-generation industrial revolution. In this context, Unmanned Aerial Vehicles (UAVs)-based low-altitude networks are expected to be the engines that drive industrial development. As an attractive industry application, UAVs-based intelligent logistics has been widely investigated to achieve a fully automated distribution manner without the aid of a workforce. However, it is difficult to perform real-time DT implementations due to limited computing resources and the high mobility of UAVs. To address the mentioned problems, we propose a Versatile DT (VerDT) framework operating at the edge. It can enable a double DT cooperation manner with a resource scheduling model and a path planning model for real-time and accurate logistics distributions. The resource scheduling model can implement the integration of computing and communication resources among UAVs for feasible cooperative distribution decisions. With the decisions, the path planning model can imitate to derive positions and velocities of UAVs for low-latency distribution performance with energy saving. Experiment results demonstrate the efficiency of our VerDT framework. Compared to state-of-the-art logistics distribution solutions, our solution reduces the distribution latency by 63.9% while improving the successful distribution ratio by 10.9%.

With the development of the future wireless communication technology and the Internet of Things (IoT), the digital twin (DT) system has become a new enabler for high-efficiency sensing in industrial applications. However, traditional DT designers may encounter a challenging situation for highly dynamic mobile entities in large-scale unmanned aerial vehicle (UAV) application scenarios. It has a direct influence on accurate and real-time sensing. To address the issue, we propose a hierarchical DT-enhanced cooperative sensing architecture. We proposed an intelligent DT model acquisition algorithm for real-time DT model construction. The accuracy of DT models is improved through our proposed model aggregation algorithm for accurate cooperative sensing. In addition, we propose a model transfer algorithm to perform a real-time cooperative sensing manner. We demonstrate the effectiveness of the proposed architecture using a multitarget tracking case study. The results show that our solution provides an accurate and real-time mobile sensing performance in the case study, with up to 90% sensing accuracy, under an acceptable system latency, compared to the traditional centralized and distributed DT manners.

With the development of communication networks and Artificial Intelligence (AI) technologies, Digital Twin (DT) now emerges to support various applications such as engineering, monitoring, controlling, healthcare and the optimization of cyber-physical systems. There is an increasing demand to create DTs that can represent physical entities for improving operational efficiency. A conventional DT consists of monitoring, imitation, and feedback control. However, conventional DTs cannot ensure efficient real-time imitation due to the high dynamics of physical systems such as UAV-based target tracking scenario. To address this issue, we propose a federated DT framework to support the imitation of mobile systems. It can guarantee real-time and accurate imitations under the prerequisite of comprehensive information acquired by a cooperative collection algorithm with the aid of UAVs. The framework can rapidly aggregate local DT models using an attention-based mechanism to improve mobile imitation accuracy. Additionally, we propose a multimodal-based DT inspection algorithm that can correct the postures of UAVs affected by winds for reliable imitations. We implement the framework in Gazebo. Our system simulations demonstrate the efficiency of the proposed federated DT framework. Our solution can reduce the imitation latency by an average of 68.4%, meanwhile, can improve the imitation accuracy by 16.4% on average when compared to traditional centralized and distributed imitation schemes.

The development of the intelligent Internet of Things has facilitated the adoption of high-efficiency Multiple Targets Tracking (MTT) in many civil security applications. However, existing MTT technologies cannot offer full capability in accurate and real-time MTT for civil security. Many attractive applications in the next-generation wireless network, like Unmanned Aerial Vehicle (UAV) swarm, are envisioned to be exploited for enhanced MTT with the advantage of flexibility. Nonetheless, highly dynamic moving targets impose some new challenges. UAVs cannot always perform expected cooperative tracking in conventional architectures as well. To address these problems, we design a tiered Digital Twin-assisted tracking framework in this paper, which leverages multi-grained imitation for real-time and accurate MTT. We imitate a coarse-grained MTT to ensure a high successful tracking ratio. We then design a fine-grained imitation with a reaction-diffusion mechanism to explore the feasible cooperators based on trajectory prediction. Hardware-in-the-loop simulations demonstrate that our tiered framework can reduce 66.7% of the system latency overhead compared to the conventional DDPG benchmark while improving the successful tracking ratio by 30.6%.

With the development of Artificial Intelligence (AI) technology, diverse Internet of Things (IoT) devices digesting abundant data have been exploited to meet more application requirements. In this regard, Unmanned Aerial Vehicle-based Multiple Targets Tracking (UAV-MTT) applications have been paid attention to processing a vast amount of sensing information for accurate and consecutive MTT. However, this application exposes imperative computing requirements on resource-limited UAVs. Edge computing can provide extra resources to alleviate the computing pressure for high-efficiency tracking decisions. Nonetheless, it is challenging to dynamically allocate UAVs for optimal association with time-varying target trajectories. To address the mentioned problems, we propose a terminal-edge cooperative tracking framework with a cross-layer resource cooperation method. In this design, we propose an auction-based cooperative game algorithm to implement highly accurate trajectory prediction. We then propose a graph learning-based tracking algorithm to adaptively manage the dynamic UAV topology for consecutive MTT. Simulation results demonstrate that our algorithm improves 70% prediction accuracy compared to other benchmarks while saving 40% energy consumption.

Cellular vehicle-to-vehicle (V2V) communications can support advanced cooperative driving applications such as vehicle platooning and extended sensing. As the safety critical applications require ultra-low communication latency and deterministic service guarantee, it is vital to characterize the latency upper bound of cellular V2V communications. However, the contention-based Medium Access Control (MAC) and dynamic vehicular network topology brings many challenges to model the upper bound of cellular V2V communication latency and assess the link capability for quality of service (QoS) guarantee. In this paper, we are motivated to reduce the research gap by modelling the latency upper bound of cellular V2V with network calculus. Based on the theoretical model, the probability distribution of the delay upper bound can be obtained under the given task features and environment conditions. Moreover, we propose an intelligent scheme to reduce upper bound of end-to-end latency in vehicular platoon scenario by adaptively adjusting the V2V communication parameters. In the proposed scheme, a deep reinforcement learning model is trained and implemented to control the time slot selection probability and the number of time slots in each frame. The proposed approaches and the V2V latency upper bound are evaluated by simulation experiments. Simulation results indicate that our network calculus based analytical approach is effective in terms of the latency upper bound estimations. In addition, with fast iterative convergence, the proposed intelligent scheme can significantly reduce the latency by about 80% compared with the conventional V2V communication protocols.

Various interconnected Internet of Things (IoT) devices have emerged, led by the intelligence of the IoT, to realize exceptional interaction with the physical world. In this context, UAV swarm-enabled Multiple Targets Tracking (UAV-MTT), which can sense and track mobile targets for many applications such as hit-and-run, is an appealing topic. Unfortunately, UAVs cannot implement real-time MTT based on the traditional centralized pattern due to the complicated road network environment. It is also challenging to realize low-overhead UAV swarm cooperation in a distributed architecture for the real-time MTT. To address the problem, we propose a cyber-twin-based distributed tracking algorithm to update and optimize a trained digital model for real-time MTT. We then design a distributed cooperative tracking framework to promote MTT performance. In the design, both short-distance and long-distance distributed tracking cooperation manners are firstly realized with low energy consumption in communication by integrating resources of sensing and communication. Resource integration promotes target sensing efficiency with a highly successful tracking ratio as well. Theoretical derivation proves our algorithmic convergence. Hardware-in-the-loop simulation results demonstrate that our proposed algorithm can remarkably save 65.7% energy consumption in communication compared to other benchmarks while efficiently promoting 20.0% sensing performance.

Driven by the development of the smart Internet of Things (IoT), unmanned aerial vehicle (UAV) swarms have been widely applied to implement diverse sensing tasks for many IoT applications. By integrating resources of UAVs, a UAV swarm can collaboratively collect and process massive image data for fast system response. However, it is difficult to reduce the computing delay caused by overlapping sensing operations and insufficient computing resources. In addition, transmission delays among UAVs may be intensified due to limited bandwidth resources. To address the mentioned challenges, we propose a UAV-swarm-based hierarchical network architecture to jointly schedule sensing, computing, and communication resources. Specifically, multiple computing groups that are formed by UAVs execute image processing in a pipeline manner to improve computing resource utilization. In order to reduce task execution time, we formulate a nonlinear integer optimization problem for the coordination of heterogeneous resources. A multiagent reinforcement learning (MARL)-based algorithm is designed to find the optimal joint resource allocation strategy under sensing accuracy constraints. Simulation results demonstrate that our algorithm reduces the task execution time while significantly improving the computing resource utilization.

Edge computing has emerged as a prospective paradigm to meet ever-increasing computation demands in mobile target tracking wireless sensor networks (MTT-WSNs). This paradigm can offload time-sensitive tasks to sink nodes to improve computing efficiency. Nevertheless, it is intractable to execute dynamic and critical missions in the MTT-WSN network due to static property. Besides, the network cannot ensure consecutive tracking with limited energy. To address the problems, this article proposes a new hierarchical tracking structure based on the edge intelligence (EI) technology. The structure can integrate the computing resource of both mobile nodes and edge servers to provide high-efficient computing for real-time tracking. Based on the proposed structure, we propose a long-term dynamic resource allocation algorithm to obtain the optimal resource scheduling solution for accurate and consecutive tracking. Simulation results demonstrate that our algorithm outperforms the deep${Q}$-learning over 14.5% in terms of systematic energy consumption. It can also obtain a significant enhancement in tracking accuracy compared with the noncooperative scheme.

With the advantages of easy deployment and flexible usage, unmanned aerial vehicle (UAV) has advanced the multitarget tracking (MTT) applications. The UAV-MTT system has great potentials to execute dull, dangerous, and critical missions for frontier defense and security. A key challenge in UAV-MTT is how to coordinate multiple UAVs to track diverse invading targets accurately and consecutively. In this article, we propose a UAV swarm-based cooperative tracking architecture to systematically improve the UAV tracking performance. We design an intelligent UAV swarm-based cooperative algorithm for consecutive target tracking and physical collision avoidance. Moreover, we design an efficient cooperative algorithm to predict the trajectory of invading targets accurately. Our simulation results demonstrate that the swarm behaviors stay stable in realistic scenarios with perturbing obstacles. Compared with state-of-the-art solutions, such as the matched deep$Q$-network, our algorithms can increase tracking accuracy by 60%, reduce tracking delay by 23%, and achieve physical collision-avoidance during the tracking process.

Vehicle platooning is one of the advanced driving applications expected to be supported by the 5G vehicle to everything (V2X) communications. It holds great potentials on improving road efficiency, driving safety and fuel efficiency. Apart from the organization and internal communication of the platoons, real-time prediction of surrounding road users (such as vehicles and cyclists) is another critical issue. While artificial intelligence (AI) is receiving increasing interests on its application to trajectory prediction, there is a potential problem that the pre-trained neural network models may not well fit the current driving environment and needs online fine-tuning to maintain an acceptable high prediction accuracy. In this paper, we propose a digital twin based real-time trajectory prediction scheme for platoons of connected intelligent vehicles. In this scheme the head vehicle of a platoon senses the surrounding vehicles. A LSTM neural network is applied for real-time trajectory prediction with the sensing outcomes. The head vehicle controls the offloading of the trajectory data and maintains a digital twin to optimize the update of LSTM model. In the digital twin a Deep-Q Learning (DQN) algorithm is utilized for adaptive fine tuning of the LSTM model, to ensure the prediction accuracy and minimize the consumption of communication and computing resources. A real-world dataset is developed from the KITTI datasets for simulations. The simulation results show that the proposed trajectory prediction scheme can maintain a prediction accuracy for safe platooning and reduce the delay of updating the neural networks by up to 40%.

Research on the sixth-generation cellular networks (6G) is gaining huge momentum to achieve ubiquitous wireless connectivity. Connected autonomous vehicles (CAVs) is a critical vertical application for 6G, holding great potentials of improving road safety, road and energy efficiency. However, the stringent service requirements of CAV applications on reliability, latency, and high speed communications will present big challenges to 6G networks. New channel access algorithms and intelligent control schemes for connected vehicles are needed for 6G-supported CAV. In this article, we investigated 6G-supported cooperative driving, which is an advanced driving mode through information sharing and driving coordination. First, we quantify the delay upper bounds of 6G vehicle-to-vehicle (V2V) communications with hybrid communication and channel access technologies. A deep learning neural network is developed and trained for the fast computation of the delay bounds in real-time operations. Then, an intelligent strategy is designed to control the intervehicle distance for cooperative autonomous driving. Furthermore, we propose a Markov chain-based algorithm to predict the parameters of the system states, and also a safe distance mapping method to enable smooth vehicular speed changes. The proposed algorithms are implemented in the AirSim autonomous driving platform. Simulation results show that the proposed algorithms are effective and robust with safe and stable cooperative autonomous driving, which greatly improve the road safety, capacity, and efficiency.

Advanced sensor technology and emerging Internet of Vehicles (IoV) have significantly accelerated the realization of autonomous driving. In operating an autonomous vehicle, traffic information needs to be collected and processed under strict delay constraints. But an individual vehicle equipped with few types of sensors and limited computation resources could not achieve precise environmental awareness and real-time information processing. Vehicular cooperative sensing and edge computing are promising approaches to address these problems. However, various types of sensing tasks and heterogeneous smart vehicles with different computing power make the cooperation between vehicles a complicated problem. To cope this problem, we form multiple vehicles into platoons, and design a novel cooperative sensing architecture. Moreover, we fully exploit unoccupied computation resources of smart vehicles, and propose a vehicular edge serving scheme, which jointly schedules cooperative sensing and task offloading. Numerical results demonstrate that our proposed scheme outperforms traditional approaches with lower delay costs.