Sustainable energy supply and high-speed communications are two significant needs for the upcoming 6G applications. This paper introduces a self-aligning resonant beam system for simultaneous light information and power transfer (SLIPT), employing a novel coupled spatially distributed resonator (CSDR). The system utilizes a resonant beam for efficient power delivery and a second-harmonic beam for concurrent data transmission, inherently minimizing echo interference and enabling bidirectional communication. Through comprehensive analyses, we investigate the CSDR’s stable region, beam evolution, and power characteristics in relation to working distance and device parameters. Numerical simulations validate the CSDR-SLIPT system’s feasibility by identifying a stable beam waist location for achieving accurate mode-match coupling between two spatially distributed resonant cavities and demonstrating its operational range and efficient power delivery across varying distances. The research reveals the system’s benefits in terms of both safety and energy transmission efficiency. We also demonstrate the trade-off among the reflectivities of the cavity mirrors in the CSDR. Besides, an experiment was conducted to verified the feasibility of self-aligning beam generation and safety under the designed structure. These findings offer valuable design insights for resonant beam systems, advancing SLIPT with significant potential for remote device connectivity.

Hate speech proliferating on social media disrupts the harmony of the Internet, making its detection a challenging task in natural language processing. Despite the recent advances in hate speech detection based on pre-trained language models (PLMs), their large parameter scale limits their applicability on resource-constrained devices, and the substantial noise and data imbalance in online speech severely weaken the model’s ability to extract valid information. To address these issues, we propose a novel robust knowledge distillation framework for improving hate speech detection. This framework aims to leverage the knowledge of a complex teacher model to supervise the training of a compact student model. Specifically, we perform linguistically motivated denoising to mitigate the impact of non-semantic noise on model training, and then transfer the fine-tuned teacher’s knowledge to the student for model compression. To handle data imbalance, we incorporate focal loss into knowledge distillation to enhance the model’s discriminative capability on hard samples. Moreover, we design a dual-round data augmentation strategy to improve model robustness against noisy and perturbations. Experiments on the SE and DV hate speech datasets reveal that our framework boosts the lightweight model’s F1-score by up to 4.3% over the state-of-the-art baseline, while reducing inference time by nearly 40% and resource consumption by 35%–50%.

Traffic prediction is a cornerstone of intelligent transportation systems (ITSs). The effectiveness of existing spatiotemporal graph neural networks (STGNNs) heavily relies on the independent identically distributed (i.i.d.) assumption of traffic data, which is frequently violated in practice because of distribution shifts owing to exogenous factors. While learning features that remain stable across all environments is promising for modeling robust frameworks, the fundamental challenge involves the decomposition of invariant features from the dynamic nature of spatiotemporal dependencies. In this article, we propose the disentangled spatiotemporal (DIST) graph neural networks, a novel framework for robust traffic forecasting considering distribution shifts. In DIST, latent invariant variables are explicitly decoupled from dynamically evolving spatiotemporal dependencies, enabling the learning of topology-agnostic representations resilient to distribution shifts. Specifically, we formulate a causality-driven learning objective that guides the separation of invariant variables from various exogenous factors. We then propose a spatiotemporal graph modeling module that can adaptively capture spatiotemporal dependencies in evolving traffic systems. Furthermore, we present a graph perturbation module to simulate topology variations during training, thereby encouraging the model to identify perturbation-sensitive dependencies and infer invariant and variant features for prediction and intervention tasks. The prediction risk and its variance on multiple interventional distributions are minimized in our learning strategy, allowing the model to identify invariant features, thus improving its robustness. The results of comprehensive real-world experiments demonstrate the superiority of our approach. The source code is available: https://github.com/tingwang25/DIST.

Autonomous driving simulators provide an effective and low-cost alternative for evaluating or enhancing visual perception models. However, the reliability of evaluation depends on the diversity and realism of the generated scenes. Extreme weather conditions, particularly extreme rainfalls, are rare and costly to capture in real-world settings. While simulated environments can help address this limitation, existing rainy image synthesizers often suffer from poor controllability over illumination and limited realism, which significantly undermines the effectiveness of the model evaluation. To that end, we propose a learning-from-rendering rainy image synthesizer, which combines the benefits of the realism of rendering-based methods and the controllability of learning-based methods. To validate the effectiveness and generalizability of our extreme rainy image synthesizer on the semantic segmentation task, a continuous set of pixel-accurately labeled extreme rainy images is necessary. By integrating the proposed synthesizer with the CARLA driving simulator, we develop CARLARain—an extreme rainy street scene simulator which can obtain paired rainy-clean images and labels under complex illumination conditions. Qualitative and quantitative experiments validate that CARLARain can effectively improve the accuracy of semantic segmentation models in extreme rainy scenes, with the models’ accuracy (mIoU) improved by \(5{-}8\%\) on the synthetic dataset and significantly enhanced in real extreme rainy scenarios under complex illuminations. Our source code and datasets are available at https://kb824999404.github.io/HRIG/ .

Vision Transformers (ViTs) leverage the attention mechanism for feature extraction but often suffer from high computational costs. To address this issue, prior works have introduced token reduction methods involving fixed-window local merging and global Bipartite Matching. However, these methods face significant challenges, such as insufficient merging due to fixed-size local windows and incorrect merging of informative tokens in global merging. To overcome these limitations, we propose Efficient Semantic Segmentation via Token Joint Merging (ESTJ) for ViT-based semantic segmentation networks. Specifically, ESTJ merges tokens using two strategies: Hierarchical Condition Pooling (HCP), which employs hierarchical local windows to effectively select sufficient tokens, and Protected Bipartite Matching (PBM), designed to preserve informative tokens using average similarity between a token and all other tokens. Experimental results demonstrate that ESTJ improves throughput by 75%, reduces GFLOPs by 40%, and enhances mIoU by up to 1.1%. Moreover, ESTJ can adjust the merging threshold during inference to adapt to scenarios that prioritize efficiency or accuracy. Compared to existing methods, ESTJ achieves a better balance between computational efficiency and segmentation accuracy.

In urban planning, traffic flow prediction, a core component of Intelligent Transportation Systems, has made significant progress with the development of deep learning. The key problem of traffic flow prediction lies in capturing the complex spatio-temporal correlations in traffic flow. In recent years, more and more research has tended to apply Transformer-based models to solve this problem. However, Transformer-based models have two major limitations for traffic flow prediction: i) Most methods only focus on extracting data features within the attention head, while ignoring the correlation between these heads, making it difficult to integrate the multi-features of traffic data; ii) Most methods do not recognize the unique impact of nodes that serve as pivotal traffic hubs in the traffic networks, which cause the Transformer to excessively focus on the influence of non-pivotal nodes. In this study, we propose a novel Transformer-based model, the Multi-Feature Fusion Transformer (MF2former), aimed at addressing the above limitations of traffic flow prediction. MF2former incorporates the Augmented Synergistic Transformer Module to achieve a comprehensive multi-feature fusion of traffic data by enhancing the information capacity within self-attention heads and performing information fusion between these heads. Additionally, our model incorporates the Pivotal Node Module, which extracts pivotal nodes from all nodes and masks the global receptive field of the Transformer to enhance its focus on pivotal nodes in the traffic network. Our model is evaluated using two real-world traffic datasets, demonstrating superior performance compared to existing methods. This study provides a stable framework for accurate traffic flow prediction, offering valuable insights for urban planners and commuters.

Human mobility restrictions are considered effective measures for epidemic mitigation but require adaptability to complex transmission environments and consistency across spatial scales. Existing mainstream approaches, including model predictive control (MPC) and reinforcement learning (RL), still face limitations. MPC relies on precise mathematical models and struggles to handle large-scale dynamic scenarios. Meanwhile, RL suffers from the curse of dimensionality, making fine-grained control challenging. In this work, we propose a novel epidemic multi-scale Hierarchical Control framework based on Reinforcement Learning and Model Predictive Control (HC-RL-MPC). At the high level, RL generates regional mobility restriction quota to balance medical and socioeconomic. At the low level, MPC clusters optimize the inter-subregion mobility quota allocation under high-level constraints. Furthermore, to ensure cross-scale policy consistency, we introduce a Policy Inverse Guidance (PIG) mechanism, where low-level modules provide gradient feedback and real-time results to high-level policy. Experimental results demonstrate that HC-RL-MPC generates macro-micro consistent mobility restriction strategies. Compared with existing models, it significantly reduces training complexity and improves cumulative rewards, providing an efficient solution for multi-scale dynamic decision-making.

Resource allocation (RA) has been considered as a key technique to achieve the optimal system performance in symbiotic radio (SR) systems by optimizing system parameters. However, most of the existing works only consider the ideal hardware conditions or perfect channel information, where the system performance of the above algorithms may be degraded under imperfect channel state information (e.g., channel estimation errors) and unideal hardware conditions (e.g., distortion noises). In order to improve transmission robustness and information security, in this paper, we study the robust secure RA problem for a multiple-input single-output SR system under channel uncertainties and hardware impairments (HWIs) with an eavesdropper. The robust RA problem with bounded channel uncertainties is formulated to maximize the total energy efficiency (EE) of the system under the minimum energy-harvesting constraint of each backscatter device (BD), the maximum transmit power constraint of the primary base station, the minimum secrecy rate of each BD, the decoding constraint, as well as the reflection coefficient constraint. To address the non-convex optimization problem, the original robust RA problem with the infinite constraints is converted into a deterministic one via a worst-case approach. Then, the objective function is transformed into a non-fractional form by using the Dinkelbach’s method. After that, the above problem is converted into a convex problem based on S-Procedure and the eigenvalue decomposition approach, and an iterative-based robust secure RA algorithm is proposed via an alternating optimization principle. Simulation results demonstrate that the proposed algorithm has lower outage probabilities and higher EE compared to the non-robust algorithm and the RA algorithm without HWIs.

Pedestrian trajectory prediction grapples with the demanding feat of modeling complex interactions and learning multimodal distribution to navigate different human-centric environments. Despite superior performance in reducing distance-based metrics, recent works tend to predict out-of-distribution trajectories, as the distribution of forthcoming paths comprises a blend of various manifolds that may be disconnected. These unrealistic trajectories can potentially jeopardize the safety of traffic participants and result in significant damage. To meet these challenges, we propose DMPred, a graph-based generator adversarial network that generates realistic multimodal trajectory predictions by better modeling the social interactions of pedestrians across different scenes in disconnected manifolds. The core of DMPred is an attentive radiate graph sequence constructed by considering the localized influence radiating from pedestrian movements, which is followed by a spatiotemporal extractor that stores and reuses potentially forgotten neighboring pedestrian information to allow for better extraction of complex interactions. Additionally, a collection of generators is utilized for forecasting, which incorporates spectral clustering on trajectories during the prior learning process of multiple generators to help reduce model redundancy and enhance flexibility for various prediction scenarios. Through extensive experiments on multiple real-world and simulation datasets, we demonstrate that DMPred obtains highly competitive results with efficacy in predicting realistic multimodal trajectories.

Predicting future frames in videos is crucial for motion understanding and behavior analysis. However, despite significant advancements, existing stochastic methods have insufficient utilization of motion patterns, leading to blurry motion in long-term predictions. Most of the previous work also lacks constraints to effectively address the unconstrained nature of spacetime-varying motion. In this paper, we propose a stochastic video prediction model based on coupled GANs. The pair of GANs could model motion trends based on adjacent frames organized in sequential and reverse orders, respectively. We assume a common latent space assumption and build bridges between forward prediction and backward prediction by leveraging the constraints of weight-sharing and cycle- consistency. Specifically, we propose to learn a joint distribution with adjacent frames in opposite orders drawn from the marginal distributions and enhance forward prediction with an in-depth exploration of motion patterns. Through experiments on several challenging datasets that include spacetime-varying human motion, we show that our model surpasses the performance of state-of-the-art models, thus validating the effectiveness of our proposed approach.

Unmanned aerial vehicle (UAV) delivery in urban environments demonstrates significant growth potential due to its efficiency and eco-friendliness. The challenges of autonomous navigation and obstacle avoidance in complex environments are crucial study aspects of UAV delivery. This paper proposes a depth camera-LiDAR fusion based UAV autonomous navigation protocol, enabling autonomous navigation and obstacle avoidance for UAV parcel delivery in complex urban environments. Experiments are conducted in a highly realistic simulation environment to validate performance of the proposed method. The results indicate that the proposed method can efficiently and accurately achieve autonomous navigation and obstacle avoidance with high robustness.

Positioning and power transfer are crucial demands in the existing Internet of Things networks, where intracavity laser-based systems are proposed as a potential alternative for providing sufficient wireless power and high-accuracy positioning simultaneously. However, existing intracavity laser-based systems still face challenges in improving power transfer efficiency and system Field of View (FoV). This article proposes a joint sensing and power transfer (JSPT) system based on distributed coupled-cavity laser (DCCL) design. Power efficiency and FoV are enhanced owing to the external-cavity feedback in DCCL. The angle of arrival estimation based on the intrinsic self-alignment feature and polarization self-modulation ranging based on the self-mixing feature are achieved in the DCCL-based JSPT system. Moreover, we build analytical models for revealing the principle of DCCL and verifying the system performance relying on diffraction propagation-based beam field simulation and rate equation-based gain simulation. Numerical results demonstrate that DCCL-based JSPT achieves 4-W charging power and mm-level 3-D positioning within an FoV of ±40° and 2-m vertical distances, showing its capability for Internet of Things applications.

Electricity theft can cause economic damage and even increase the risk of outage. Recently, many methods have implemented electricity theft detection on smart meter data. However, how to conduct detection on the dataset without any label still remains challenging. In this article, we propose a novel unsupervised two-stage approach under the assumption that the training set is contaminated by attacks. Specifically, the method consists of two stages: (1) a Gaussian mixture model is employed to cluster consumption patterns with respect to different habits of electricity usage, and with the goal of improving the accuracy of the model in the posterior stage; (2) an attention-based bidirectional long short-term memory encoder-decoder scheme is employed to improve the robustness against the non-malicious changes in usage patterns leveraging the process of encoding and decoding. Quantifying the similarity of consumption patterns and reconstruction errors, the anomaly score is defined to improve detection performance. Experiments on a real dataset show that the proposed method outperforms the state-of-the-art unsupervised detectors.

Simultaneous lightwave information and power transfer (SLIPT) is a potential way to meet the demands of sustainable power supply and high-rate data transfer in next-generation networks. Although resonant beam-based SLIPT (RB-SLIPT) can realize high-power energy transfer, high-rate data transfer, human safety, and self-alignment simultaneously, mobile transmission channel (MTC) analysis under non-line-of-sight (NLOS) propagation has not been investigated. In this paper, we propose analytical models and simulation tools for reflector-assisted NLOS transmission of RB-SLIPT, where transmission loss and accurate beam field profile of NLOS MTC can be obtained with a receiver at arbitrary positions and attitude angles. We establish analytical models relying on full diffraction theory for beam propagation between tilted or off-axis planes. Then, we provide three numerical methods (i.e., NUFFT-based, cubic interpolation-based, and linear interpolation-based methods) in simulations. Moreover, to deal with the contradiction between limited computing memory and high sampling requirements for long-range transmission analysis, we propose a multi-hop sliding window approach, which can reduce the sampling number by a factor of thousands. Finally, numerical results demonstrate that RB-SLIPT can achieve 3W charging power and 10bit/s/Hz data rate over a 2m distance in NLOS scenarios.

To deal with the discrepancy between global and local objectives in the federated learning invoked by the non-independent, identically distributed (non-IID) data and mitigate the impact of catastrophic forgetting in the training phase, we propose a federated learning framework with data distribution-wise reinforcement learning to perform node selection to accelerate the convergence process and alleviate the accuracy degradation. In this framework, the agent on the central server observes the number of samples every node owns, the derived distribution information of every dataset, and the current local and global accuracy. Then infer the selected node-set to participate in the current federated learning round through policy network in reinforcement learning. Finally, we conduct simulations with publicly data sets. Simulation results indicate that our FedWNS outperforms the existing FedAvg and CSFedAvg on the testing accuracy and the communication rounds to reach target accuracy under different settings.

The self-protection resonant beam system (RBS) is a promising long-range and high-power simultaneous wireless information and power transfer (SWIPT) scheme for energy-constrained Internet of Things (IoT) devices, which can achieve safe power and information transfer without mechanical control measures. In the system, a portion of the emitted resonant beam (RB) is reflected and refracted to form protective beams encircling the RB in 360° degrees. In this article, we propose an external object invasion model to evaluate the safety performance of self-protection RBS. With the invading of external object, the field propagation mode of the protective beam shifts, leading to the change of the pumping power threshold of the system, which controls the presence or absence of RB. The numerical results show that the maximal irradiance on invading object is around$0.5 \rm {W/cm^{2}}$at 2-$\rm {m}$transmission distance, with approximately 3-$\rm {W}$output electric power and 12-$\rm {bps/Hz}$spectral efficiency, which is less than the maximum permissible exposure (MPE) requirement for the human skin of$1 \rm {W/cm^{2}}$in the standard “safety of laser products IEC 60825-1.” As a result, the self-protection RBS can achieve high-range, high-power, and human-safe SWIPT.

Long-range, high-power wireless power transfer (WPT) and high-capacity communication can be achieved simultaneously in the resonant beam system (RBS), characterized with spatially separated transmitter and receiver. However, human safety in space transmission cannot be guaranteed if the transmitted power is above a certain level (e.g., several Watts). Thus, in this article, we propose a self-protection RBS, in which the protective beams embrace the energy-transfer resonant beam and are formed by the refracting part of the resonant beam emitted from the output reflector. If an external object comes across the protective beam whose power is very low, the protective beam transmission is cut off. Meanwhile, the resonant beam is interrupted due to the limit of excitation threshold. Then, we reveal the self-protection mechanism based on electromagnetic field propagation, self-mixing interference effect, and output power model. Afterward, we demonstrate that safe energy transfer can be realized by pumping gain medium with a pumping power that is greater than the threshold of the self-protection RBS and less than that of the unprotected RBS. Finally, the numerical results show that about 4.6-W electric power and 12.8 bps/Hz spectral efficiency can be transmitted at 2-m transmission distance safely in the self-protection RBS. Hence, the self-protection RBS provides a new way for safe simultaneous wireless information and power transfer (SWIPT) without mechanical control.

The surround-view module is an indispensable component of a modern advanced driving assistance system. By calibrating the intrinsics and extrinsics of the surround-view cameras accurately, a top-down surround-view can be generated from raw fisheye images. However, poses of these cameras sometimes may change. At present, how to correct poses of cameras in a surround-view system online without re-calibration is still an open issue. To settle this problem, we introduce the sparse direct framework and propose a novel optimization scheme of a cascade structure. This scheme is actually composed of two levels of optimization and two corresponding photometric error based models are proposed. The model for the first-level optimization is called the ground model, as its photometric errors are measured on the ground plane. For the second level of the optimization, it’s based on the so-called ground-camera model, in which photometric errors are computed on the imaging planes. With these models, the pose correction task is formulated as a nonlinear least-squares problem to minimize photometric errors in overlapping regions of adjacent bird’s-eye-view images. With a cascade structure of these two levels of optimization, an appropriate balance between the speed and the accuracy can be achieved. Experiments show that our method can effectively eliminate the misalignment caused by cameras’ moderate pose changes in the surround-view system. Source code and test cases are available online at https://cslinzhang.github.io/CamPoseCorrection/ .

Simultaneous lightwave information and power transfer (SLIPT) has been regarded as a promising technology to deal with the ever-growing energy consumption and data-rate demands in the Internet of Things. We propose a resonant beam based SLIPT (RB-SLIPT) system, which deals with the conflict of high deliverable power and mobile receiver positioning with the existing SLIPT schemes. At first, we establish a mobile transmission channel model and depict the energy distribution in the channel. Then, we present a practical design and evaluate the energy/data transfer performance within the moving range of the RB-SLIPT. Numerical evaluation demonstrates that the RB-SLIPT can deliver more than 4W charging power and enable 3Gb/s achievable data rate with the moving range of 20° field of view (FOV) over 3m distance. Thus, RB-SLIPT can enable simultaneous high deliverable power and high data rate in mobile scenarios without tracking control.

Optical wireless communications (OWC) utilizing infrared or visible light as the carrier attracts great attention in 6G research. Resonant beam communications (RBCom) is an OWC technology which simultaneously satisfies the needs of non-mechanical mobility and high signal-to-noise ratio (SNR). It has the self-alignment feature and therefore avoids positioning and pointing operations. However, RBCom undergoes echo interference. Here we propose an echo-interference-free RBCom system design based on second harmonic generation. The transmitter and the receiver constitute a spatially separated laser resonator, in which the retro-reflective resonant beam is formed and tracks the receiver automatically. This structure provides the channel with adaptive capability in beamforming and alignment, which is similar to the concept of intelligent reflecting surface (IRS) enhanced communications, but without hardware and software controllers. Besides, we establish an analytical model to evaluate the beam radius, the beam power, and the channel capacity. The results show that our system achieves longer distance and smaller beam diameter for the transmission beyond 10 Gbit/s, compared with the existing OWC technologies.

Wireless energy transfer (WET) has recently emerged as an appealing solution for power supplying mobile/Internet of Things (IoT) devices. As an enabling WET technology, resonant beam charging (RBC) is well documented for its long-range, high-power, and safe “WiFi-like” mobile power supply. To provide high-quality wireless charging services for multiple users in a given region, we formulate a deployment problem of multiple RBC transmitters for balancing the charging fairness and quality of charging service. Based on the RBC transmitter's coverage model and receiver's charging/discharging model, a genetic algorithm (GA)-based scheme and a particle swarm optimization (PSO)-based scheme are put forth to resolve the above issue. Moreover, we present a scheduling method to evaluate the performance of the proposed algorithms. The numerical results corroborate that the optimized deployment schemes outperform uniform and random deployment in 10%-20% charging efficiency improvement.

The vision and requirements of the sixth generation (6G) mobile communication systems are expected to adopt freespace optical communication (FSO) and wireless power transfer (WPT). The laser-based WPT or wireless information transfer (WIT) usually faces the challenges of mobility and safety. We present a mobile and safe resonant beam communication (RBCom) system, which can realize high-rate simultaneous wireless information and power transfer (SWIPT). We propose an analytical model to depict its carrier beam and information transfer procedures. The numerical results show that RBCom can achieve more than 40 mW charging power and 1.6 Gbit/s channel capacity with orthogonal frequency division multiplexing (OFDM) scheme, which can be applied in future scenario where power and high-rate data are simultaneously desired.