Integrated Sensing and Communication (ISAC) holds great promise for enabling event-level sensing, such as behavioral intention prediction (BIP) in autonomous driving, particularly under non-line-of-sight (NLoS) or adverse weather conditions where conventional sensors degrade. However, as a key instance of event-level sensing, ISAC-based BIP remains unexplored. To address this gap, we propose an ISAC-enabled BIP framework and validate its feasibility and effectiveness through extensive simulations. Our framework achieves robust performance in safety-critical scenarios, improving the F1-score by 11.4% over sensor-based baselines in adverse weather, thereby demonstrating ISAC’s potential for intelligent event-level sensing.

Edge robotics involves frequent exchanges of large-volume multi-modal data. Existing methods ignore the interdependency between robotic functionalities and communication conditions, leading to excessive communication overhead. This paper revolutionizes edge robotics systems through integrated perception, motion, and communication (IPMC). As such, robots can dynamically adapt their communication strategies (i.e., compression ratio, transmission frequency, transmit power) by leveraging the knowledge of robotic perception and motion dynamics, thus reducing the need for excessive sensor data uploads. Furthermore, by leveraging the learning to optimize (LTO) paradigm, an imitation learning neural network is designed and implemented, which reduces the computational complexity by over 10x compared to state-of-the art optimization solvers. Experiments demonstrate the superiority of the proposed IPMC and the real-time execution capability of LTO.

We propose an integrated sensing and communication (ISAC) beamforming method that performs joint multiple input multiple-output (MIMO) radar sensing and multi-user MIMO communication. Our approach builds on a matrix nearness formulation of the MIMO radar problem and utilizes our recently proposed efficient solver, where the computational complexity is dominated by an eigenvalue decomposition (EVD) evaluation at each iteration. We extend this formulation to an ISAC scenario by incorporating minimum signal-to-noise ratio constraints as communication design criteria, only requiring statistical channel state information knowledge at base station. Furthermore, we propose a method to avoid the burdensome EVD evaluations in certain iterations, reducing the computation time by up to six times in a massive MIMO setting.

Reliable automatic modulation classification (AMC) degrades under mismatched noise and propagation conditions. This letter presents a lightweight and interpretable domain-adaptive AMC framework that jointly addresses both SNR variation and channel mismatch. Modality-specific feature extractors operate on raw IQ samples and spectral representations, while a domain-alignment module combines adversarial domain confusion with covariance matching to learn domain-invariant features. Experiments on RadioML2016.10a show improved robustness under SNR mismatch, and tests on Rayleigh–Rician fading datasets across five carrier frequencies demonstrate strong cross-channel generalization, achieving up to 86.8% accuracy. The proposed models require fewer than 0.75MB of parameters and support sub-millisecond inference, supporting deployment-ready intelligent radio systems.

Millimeter-wave (mmWave) wireless backhaul is a key enabler for future 6G network densification, but its reliance on line-of-sight (LoS) propagation is a major challenge. We study relay placement for multi-hop mmWave backhaul connecting the small base stations (SBS) to the macro base station (MBS) over complex environment. While relays can circumvent blockages, optimizing their placement is complicated by directional antennas and complex environment. Interference is non-local and tightly coupled with beam pointing, routing and traffic. Environment-induced shadowing produces a highly non-convex optimization landscape, while large relay fleets generate a high-dimensional search space. We develop a network model with an outage-based performance metric that captures this direction-dependent interference and enforces graph-theoretic reliability constraints. To scale, we introduce a link-quality-based cooperative coevolution (LQBCC) algorithm that adaptively groups variables using community detection on a link-quality graph and collaboratively optimizes strongly interacting relays. Experiments on high-fidelity environment scenarios show LQBCC consistently surpasses advanced evolutionary baselines and relay-placement schemes in worst-path success probability, overall reliability, and search efficiency. At a relay density of 20 nodes/km, LQBCC achieves a 70% performance gain over the best baseline, with 10-fold greater search efficiency and zero reliability violations.

In a cell-free massive MIMO (CFmMIMO) network with a daisy-chain fronthaul, the amount of information that each access point (AP) needs to communicate with the next AP in the chain is determined by the location of the AP in the sequential fronthaul. Therefore, we propose two sequential processing strategies to combat the adverse effect of fronthaul compression on the sum of users’ spectral efficiency (SE): 1) linearly increasing fronthaul capacity allocation among APs and 2) Two-Path users’ signal estimation. The two strategies show superior performance in terms of sum SE compared to the equal fronthaul capacity allocation and Single-Path sequential signal estimation.

Multifunctional radar with Integrated Sensing and Communication (ISAC) capabilities represents a key direction in the evolution of future software-defined radar systems. However, the presence of random communication information introduces significant clutter in the Doppler dimension during coherent accumulation. Under strong scatterer echoes, this clutter may cause numerous false alarms or obscure weak targets that would otherwise be resolvable in the Doppler domain, posing a critical challenge for radar performance. To address this issue, we propose a simple and effective algorithm termed Spectrum Windowing Whitening Filtering (SWWF). The proposed method effectively eliminates the influence of embedded communication signals while suppressing range sidelobes. Its computational complexity is comparable to that of conventional matched filtering, ensuring compatibility with existing radar architectures. To validate the effectiveness of the proposed algorithm, we conducted field experiments on unmanned aerial vehicle (UAV) detection. The results demonstrate that SWWF significantly reduces Doppler-domain clutter and improves the detectability of weak targets in the presence of strong interference, thereby enhancing the overall robustness and reliability of ISAC radar systems.

The sum of random variables arises as a challenge in several wireless communication problems, particularly those characterized by the Fox H distribution. In this paper, we derive the moment generating function (MGF) of the sum of independent and non identically distributed (INID) Fox H random variables and apply the matrix exponential distribution method (MEDM) to obtain the probability distribution of this sum and to derive performance metrics such as outage probability (OP), average symbol error probability (ASEP) and normalized ergodic capacity (EC) in a wireless communication system assisted by multiple reconfigurable intelligent surfaces (RIS).