With the advent of the 5G era, high-precision localization based on mobile communication networks has become a research hotspot, playing an important role in indoor emergency rescue in shopping malls, smart factory management and tracking, as well as precision marketing. However, in complex environments, non-line-of-sight (NLOS) propagation reduces the measurement accuracy of 5G signals, causing large deviations in position solving. In order to obtain high-precision position information, it is necessary to recognize the propagation state of the signal before distance measurement or angle measurement. In this paper, we propose a dynamic multi-level optimization of comprehensive features (DMOCF) network model for line-of-sight (LOS)/NLOS identification. The DMOCF model improves the expression ability of the deep model by adding a res2 module to the time delay neural network (TDNN), so that fine-grained feature information such as weak reflections or noise in the signal can be deeply understood by the model, enabling the network to realize layer-level feature processing by adding Squeeze and Excitation (SE) blocks with adaptive weight adjustment for each layer. A mamba module with position coding is added to each layer to capture the local patterns of wireless signals under complex propagation phenomena by extracting local features, enabling the model to understand the evolution of signals over time in a deeper way. In addition, this paper proposes an improved sand cat search algorithm for network parameter search, which improves search efficiency and search accuracy. Overall, this new network architecture combines the capabilities of local feature extraction, global feature preservation, and time series modeling, resulting in superior performance in the 5G channel impulse response (CIR) signal classification task, improving the accuracy of the model and accurately identifying the key characteristics of multipath signal propagation. Experimental results show that the NLOS/LOS recognition method proposed in this paper has higher accuracy than other deep learning methods.

Integrated sensing and communication (ISAC) is emerging as a pivotal development direction for beyond-fifth-generation (B5G) and sixth-generation (6G) wireless networks, especially with the challenge of achieving the communication and sensing capabilities necessary for the future Internet of Things (IoT) paradigm under resource constraints. In this article, we propose a joint explicit communication and implicit sensing (JECIS) system designed to generate sensing and communication signals across two distinct domains, thereby enabling the multiplexing of the same time and frequency resources. The proposed system generates a block-shaped sensing reference signal in the delay-Doppler domain to facilitate the estimation of relative range and velocity between the transmitter and the receiver, while communication signals are produced in the time-frequency domain. Furthermore, we introduce a two-step algorithm for range and velocity estimation that achieves high precision while ensuring exceptional noise resilience and low complexity. The simulation results indicate that the proposed method effectively achieves high sensing performance while the sensing signal operates at a significantly lower power level in comparison to communication signals, rendering the impact on the bit error rate (BER) of communications negligible.

Vision-centric world models have shown great promise in autonomous driving, but existing autoregressive paradigms based on Transformers suffer from quadratic computational complexity and severe spatial degradation in long-horizon 4D occupancy forecasting. To address these challenges, we propose DeltaMamba, a novel kinematics-aware spatiotemporal world model. By forecasting the differential changes of the environment using State Space Models rather than reconstructing dense grids from scratch, our method achieves linear O(L) complexity and effectively mitigates long-term compounding errors.Furthermore, to bridge the critical gap between world representation and motion planning, we introduce a Kinematics-Aware Dual Attention module coupled with Codebook Reconstruction Planning. Modulated by Adaptive Layer Normalization, this architecture explicitly aligns the visual features with ego-intent, forcing the network to proactively focus on navigable corridors and potential hazards. Extensive experiments on the nuScenes dataset demonstrate that our framework establishes a new state-of-the-art. It significantly mitigates error accumulation, boosting the 4D forecasting mIoU by 49.6% relatively at the challenging 3-second horizon, while achieving highly competitive planning safety. Notably, DeltaMamba strikes an optimal balance between extreme 4D perception and safe trajectory generation, achieving an inference speed of 14.1 FPS during validation, a 43.9% relative speedup over existing baselines.

Worker location information is essential for ensuring safety in industrial environments. Fifth-generation (5G) technology’s wide coverage and comprehensive factory infrastructure make it crucial for industrial positioning. As the fundamental observation, current 5G ranging primarily relies on large bandwidth configurations, imposing stringent radio-frequency requirements and high power consumption that conflicts with the extended battery life needed for industrial devices. To address this limitation, we propose a frequency-enhanced reference signal (FERS) that enables high-precision ranging under industrial hardware constraints while maintaining low power consumption and limited bandwidth requirements. Furthermore, we develop and integrate a fine phase ranging (FPR) algorithm to achieve super-resolution distance measurement. Simulation and experimental results demonstrate that the proposed approach significantly enhances ranging accuracy under low-bandwidth constraints. The proposed FPR algorithm delivers superior accuracy while maintaining computational complexity that is an order of magnitude lower than state-of-the-art super-resolution ranging methods. Additionally, the approach exhibits strong robustness under low signal-to-noise ratio conditions.

Non-line-of-sight (NLOS) errors constitute the primary source of inaccuracies in time-of-arrival (TOA) positioning. While recent studies have successfully mitigated NLOS effects in small-scale scenarios, these methods often struggle to maintain effectiveness in long-distance localization due to the exacerbated impact of NLOS errors. This paper proposes an asynchronous TOA-based positioning method capable of achieving accurate positioning in long-distance, severe NLOS environments while accounting for clock errors. A novel abnormal TOA detection method leveraging geometric characteristics is proposed to initially mitigate the influence of NLOS errors. Additionally, an asynchronous TOA positioning algorithm based on semidefinite programming (SDP) is developed, demonstrating robust applicability even under severe NLOS conditions. Experimental results from both simulations using a parameterized error distribution model and ray-tracing simulations in long-distance scenarios confirm that the proposed method achieves high positioning accuracy despite significant NLOS interference.