With the rapid development of low-altitude economy, the low-altitude intelligent network (LAIN) serves as a critical infrastructure for supporting diversified aerial activities. However, current LAIN lacks a physical-network synchronization mechanism and fails to handle heterogeneity at the architecture level, which leads to difficulties in real-time adaptive adjustments and efficient unified coordination. To address these issues, this paper proposes the networked embodied intelligence (NEI) paradigm, with a network-level sensing-decision-action-feedback (SDAF) closed-loop mechanism to synchronize physical and network states. Building on this paradigm, we functionally reconfigure LAIN into four collaborative subnetworks: sensing, computing, communication and navigation. As a further step, we propose the NEI-LAIN architecture, where these subnetworks collaborate via the SDAF loop to achieve global collaboration and continuous evolution. Simulation results demonstrate that the proposed NEI-LAIN can significantly enhance the performance of communication robustness, resource utilization and task responsiveness in highly dynamic scenarios. Finally, we discuss its implementation challenges and future research directions.

Precise positioning and identification of unauthorized unmanned aerial vehicles (UAVs) are of crucial importance for spectrum security and privacy protection in future intelligent networks. Although various single-modality approaches have been investigated, their performance degrades under the sensor-specific noise, resulting in suboptimal performance and robustness. To address these security challenges, we propose a multi-layer radio frequency (RF)-vision fusion framework that synergistically exploits temporal-spectral features of UAV RF signals and spatial-visual information to achieve precise and robust UAV positioning and identification. Moreover, a corresponding unified RF-Vision fusion Network (RFViNet) is designed to exploit the RF-vision cross-modal complementary and semantic synergy. Specifically, by leveraging the novel RFinformed proposal generation, RF-enhanced feature modulation, and RF-guided semantic query modules, the RFViNet effectively exploits the complementary strengths of RF and visual modalities. Furthermore, a practical RF–vision platform is developed to evaluate the performance of our method under various challenging conditions. Experimental results on the real-world dataset demonstrate that the proposed method achieves a competitive 85.8% average precision AP50, highlighting its potential for enhancing the spectrum security in future intelligent wireless networks.

With the rapid development of wireless communication services, spectrum map-based localization has become an important technology in the sixth-generation (6G) wireless communication networks due to their low cost and ease of implementation. However, signal source localization based on spectrum map construction is heavily dependent on the construction accuracy of the spectrum map. This challenge is further exacerbated in urban environments due to high-density connections and complex terrain. To address the aforementioned challenges, a data-and-semantic dual-driven method is proposed, which incorporates semantic knowledge of both binary city maps and binary sampling location maps. This approach first extracts spatial dimension information that reflects signal propagation, improving the accuracy of the constructed spectrum map and signal source localization in the complex urban environments. Then, to reduce the reliance of signal source localization on the accuracy of spectrum map construction, a data-and-semantic dual-driven intelligent inference framework for simultaneously spectrum map construction and signal source localization (DSD-SCL) is proposed. Moreover, a joint training framework is employed to collaboratively optimize both spectrum map construction and signal source localization. Simulation results demonstrate that DSD-SCL exhibits superior performance in terms of stability and convergence speed. Meanwhile, it significantly enhances the construction accuracy of spectrum maps and the localization accuracy of signal sources, particularly in low sampling density and multisignal source scenarios.

With the growing use of unmanned aerial vehicles (UAVs), UAV recognition has become crucial due to emerging risks in many scenarios. Various radio frequency (RF)-based recognition methods are already in use. However, they still struggle to recognize unknown UAVs and rely heavily on bundant features derived from large-scale labeled datasets. To address this limitation, a few-shot open-set UAV recognition method is proposed. The method employs a multi-domain network and self-attention mechanism to extract and fuse features from time and frequency domains. Moreover, the extracted features are integrated into few-shot open-set recognition under the Euclidean distance criterion, incorporated with a threshold. Furthermore, experimental results demonstrate that the accuracy of proposed method achieves 85.13%, which is about 10% higher than existing open-set UAV recognition methods in few-shot scenarios, offering a solution for real-time spectrum monitoring and countermeasures against unauthorized UAVs.