Logic synthesis (LS) is a core stage in digital integrated circuit design, typically performed by applying optimized operators in Electronic Design Automation (EDA) tools. The quality of results (QoR) largely depends on the operator sequence. Traditional heuristic methods struggle with scalable circuit complexity, while existing learning-based approaches improve optimization but require retraining for each new circuit, limiting adaptability. To address this, we propose MetaSyn, a meta-reinforcement learning framework with multimodal circuit representation for adaptive logic synthesis. MetaSyn achieves both adaptability and high performance via three innovations: (1) A Model-Agnostic Meta-Learning (MAML) framework tailored for logic synthesis, where the inner and outer loops enable learning initialization parameters that allow rapid fine-tuning on unseen circuits with few samples. (2) A cooperative multistage RL environment (MSRL) with a multi-PPO architecture, dual-component action space, and delayed rewards, where three actor networks collaboratively optimize stage-specific operator sequences for higher performance and fast adaptability. (3) A general multimodal circuit representation (MCR) that fuses features from pre-trained DeepGate2 (AIGs), pre-trained Mamba (operator sequences), and an MLP (scalar states) via cross-attention and residual gating, forming a unified input for the policy network to enhance performance and generalization. Evaluations on the EPFL benchmark show that MetaSyn improves performance by up to 31.2% over compress2rs and by 20.8% over the state-of-the-art (SOTA) method, while offering significant advantages in fast adaptation to diverse circuits.

The cloud–fog automation (CFA) paradigm accelerates Industry 4.0 by enabling fully automated industrial systems through interconnected wired and wireless devices. However, dynamic uncertainties such as environment-induced network delays and disturbances challenge the stability and efficiency of these systems. To address these issues, this paper proposes a control–communication co-design framework named C3L (Control– Communication Coupling Loop), which integrates 5G and Time-Sensitive Networking (TSN) to coordinate transmission and control across cloud and fog layers. A hierarchical control strategy is introduced based on a delay threshold derived from Linear Matrix Inequality (LMI) analysis, enabling dynamic selection between cloud and fog control units for both stability and responsiveness. To ensure timely and reliable control input delivery under uncertain networks, we develop a deterministic transmission mechanism centered on a novel metric, Packet Loss Tolerance (PLT), which quantifies how many consecutive losses the system can endure while maintaining stability. Additionally, a new optimization criterion, Pareto Deviation Value (PDV), is proposed to avoid combining control and communication costs with incompatible physical units. Simulation results demonstrate that the proposed method enhances control robustness and communication efficiency in complex industrial networks.

Recently, LiDAR-based Vehicle-Infrastructure Cooperative (VIC) perception has shown an advantage in expanding the horizon of Connected Autonomous Vehicles (CAVs), enabling occlusion-aware 3D scene understanding. However, limited communication bandwidth hampers multi-agent cooperation in urban Internet of Things (IoT) environments. Existing solutions often compress or implicitly filter high-resolution features, resulting in semantic redundancy or information loss, which degrades overall performance. To tackle this, we propose VICooper, a communication-efficient VIC perception framework. Driven by the stable context of static infrastructure LiDARs, VICooper employs offline Background Mapping (BgM) to extract foreground points of interest, thereby offering explicit guidance for communication reduction. For the sparse yet critical foreground point clouds, we introduce the Multi-dimensional Foreground Backbone (MdFB) that incorporates geometric cues, including height, scale, and spatial density, to enrich feature encoding. To address the fusion imbalance between dense vehicle-side and sparse roadside features, we customize a Progressive Bilateral Feature Aggregation (PbFA) using a deformable transformer to capture inter-agent mutual correlations, thereby enabling the deep coupling of heterogeneous agents under asymmetric information. Extensive evaluations on real-world VIC benchmark validate that VICooper achieves superior performance with substantially lower bandwidth, demonstrating its potential in intelligent transportation IoT ecosystems.

Rigid gang scheduling, which enables multiple threads of real-time tasks to execute concurrently on a fixed number of different processors, has recently gained attention. Compared to preemptive rigid gang scheduling, non-preemptive rigid gang (NPRG) scheduling improves predictability by requiring fewer context switches. However, NPRG scheduling is vulnerable to 2D-blocking, where lower-priority tasks can block a higher-priority task multiple times, leading to severe priority inversion at runtime and pessimism in schedulability analysis. The root cause is the work-conserving execution behavior, in which tasks are immediately executed whenever the required processors are idle, regardless of priority and the potential blocking of subsequent tasks. This paper focuses on the global fixed-priority NPRG scheduling and introduces the NPRG-SS scheduler. NPRG-SS leverages a selective stalling (SS) mechanism that selectively stalls lower-priority jobs whenever their execution could delay the start time of a higher-priority job in the ready queue. This non-work-conserving approach inherently mitigates multiple blocking. Additionally, we present the first schedulability analysis for NPRG scheduling with SS and propose a novel heuristic priority assignment technique, Iterative Priority Refinement (IPR). Experimental results show that NPRG-SS with IPR effectively mitigates priority inversion, accepts up to 42% more task sets than the baselines at runtime, while our proposed schedulability test accepts up to 80% more task sets than the baselines in worst-case scenarios.

Place recognition (PR) is a critical component of simultaneous localization and mapping in the fields of autonomous driving and robotics. In outdoor large-scale and complex environments, existing vision-based place recognition (VPR) methods typically rely on single-camera input, which is inherently limited by its restricted field of view and, thus, vulnerable to viewpoint variations. To effectively fill the aforementioned drawbacks, we propose VI_MCPR, a novel method that supports input from any number of cameras. This method utilizes a multibranch, weight-sharing encoder structure to encode image features from multiperspective simultaneously. The robust feature attention pooling block is then utilized to learn high-order nonlinear features and latent correlations between features, effectively mitigating the loss of key features during down-sampling. To generate a discriminative global descriptor representing the image, we designed a geometry and spatial relationship enhanced block, named graph-SE-transform (GSET), which captures the overall shape of objects in a manner similar to the human visual system. Extensive comparative experiments on the NuScenes, Argoverse 2 Sensors, and real-vehicle datasets demonstrate that VI_MCPR outperforms state-of-the-art VPR methods. Compared to the strongest representative baselines, our approach increases PR performance by approximately 6% under viewpoint variations, by approximately 6% in dynamic environments, and by approximately 8% in extreme scenarios such as adverse weather, illumination changes, and low-texture conditions.

Computer-aided design (CAD) significantly enhances the efficiency, accuracy, and innovation of design processes by enabling precise 2D and 3D modeling, extensive analysis, and optimization. Existing methods for creating CAD models rely on latent vectors or point clouds, which are difficult to obtain, and storage costs are substantial. Recent advances in Multimodal Large Language Models (MLLMs) have inspired researchers to use natural language instructions and images for CAD model construction. However, these models still struggle with inferring accurate 3D spatial location and orientation, leading to inaccuracies in determining the spatial 3D starting points and extrusion directions for constructing geometries. This work introduces CAD-GPT, a CAD synthesis method with spatial reasoning-enhanced MLLM that takes either a single image or a textual description as input. To achieve precise spatial inference, our approach introduces a 3D Modeling Spatial Mechanism. This method maps 3D spatial positions and 3D sketch plane rotation angles into a 1D linguistic feature space using a specialized spatial unfolding mechanism, while discretizing 2D sketch coordinates into an appropriate planar space to enable precise determination of spatial starting position, sketch orientation, and 2D sketch coordinate translations. Extensive experiments demonstrate that CAD-GPT consistently outperforms existing state-of-the-art methods in CAD model synthesis, both quantitatively and qualitatively.

Time-Sensitive Networking (TSN) has emerged as a vital networking paradigm for timely and reliable data transmission. Recently, researchers are increasingly focusing on the scalability of algorithms for scheduling problems over diverse network topologies and flows based on deep reinforcement learning methods (DRL). However, the lack of reasonable characterization of flow conflicts and dependencies leads to limited generalization and schedulability under the discrepancies in characteristics and number of flows. To address those issues, we propose a data-driven scheduling method guided by flow sequence conflict theory, which improves generalization and schedulability over different flow characteristics and topologies. Specifically, we design a network feature encoding scheme to formulate a reasonable characterization of flow conflicts by integrating a graph-based flow sequence representation model with graph attention networks (GATs). Regarding the abovementioned characterization as the acknowledge embedding, a data-driven method is designed to learn two sub-policies in the scheduling process, including flow selection and solution searching for each selected flow. Within the scheduling process, a multi-head attention-based neural network is designed to generate the scheduling sequence of variable length, which characterizes the dependencies between flows with different numbers. Simulation results demonstrate that compared to existing DRL-based methods, the runtime of scheduling at scale is increased by at least 100 % in complex traffic scenarios while the slot utilization on the links is also improved compared to other methods.

Time Sensitive Networking (TSN) has been widely considered as a promising networking technology in industrial fields as its capibility of deterministic transmission. One of the main challenges in TSN application is the complexity of network planning, including topology design, flow routing and scheduling schemes. In these three tasks, topology design plays a vital role in reducing costs and supporting the feasibility of routing and scheduling schemes. While recent researchers make some progress in routing and scheduling algorithms, most studies lack effective approaches for optimizing network topology, limiting the practical applicability of TSN. This paper addresses this problem by presenting a joint design method (JDM) for low-cost TSN topology design while also ensuring the feasibility of flow routing and scheduling. A unified mathematical model is developed to integrate TSN topology, routing and scheduling into a joint optimization problem, minimizing the overall network cost. On this basis, a one-hot vectorization technique is applied to linearize scheduling constraints to enhance the computational efficiency. Simulation results show that compared with other methods, the proposed JDM generates TSN topology at the lowest cost, ensuring flows deterministic transmission within minutes.

With the ability to provide deterministic transmission, time sensitive networking (TSN) has been widely used in various industrial scenarios. However, most of the existing TSN research focuses on traffic scheduling over predefined network topology. In industrial applications, optimizing network topology can reduce the number of network devices and the length of cables thereby lowering material and management costs, yet considering topology within TSN scheduling greatly increases the problem’s complexity. In this article, we first incorporate topology planning and traffic scheduling together into the TSN network design problem (TDP). A mathematical model for TDP is formulated, with the objective of minimizing the total weight and cost of a TSN network while satisfying the end-to-end deterministic transmission requirements. Subsequently, we establish the metric of capacity of TSN flow groups (CoG), and the proposed CoG estimation method enables feasibility assessment of TDP solutions. Since CoG measures a network’s capacity to accommodate TSN flows, we utilize it as the evaluation metric within our heuristic algorithm, CoG analysis based TSN network design algorithm (CATDA), reducing ineffective searches and enhancing the solution efficiency of TDP. Experiments show that compared to other algorithms, the proposed CATDA achieves the lowest-cost TSN network design solution and performs over 100 times faster than other algorithms.

As an emerging communication technology, time-sensitive networking (TSN) holds the potential to enable real-time and deterministic interactions for streams within the Industrial Internet of Things. However, effectively and promptly scheduling large-scale streams in the TSN network poses a significant challenge due to high computational complexity. In this article, we conduct a schedulability analysis to preprocess the stream set with given routing paths, avoiding invalid searches and providing optimized guidance for stream routing. To accelerate the feasibility validation of potential solutions, an efficient stream conflict detection approach is proposed leveraging stream grouping with correlation analysis to compress the detection space. Integrating the above preprocess and efficient conflict detection, we develop a scalable scheduling algorithm with an incremental schedule synthesis to enhance scalability while ensuring low slot occupancy for all links. Evaluation results demonstrate that the proposed algorithm significantly reduces synthesis time and achieves low slot occupancy of all links compared to existing scheduling methods.

Industrial time-sensitive networking (TSN) is pivotal for ensuring real-time and reliable flow transmission. There is a growing focus on its scalable scheduling for time-critical flows pursuing ultralow latency and jitter. Its time-aware shaper protocol tackles uncertain delay and frame loss but introduces high scheduling complexity. However, existing works lack a scheduling feature mining mechanism. They impose unnecessarily tight rules to simplify the problem but sacrifice scheduling optimality. To address this, especially in industrial networks with large-scale complex flows, we propose a flow-overlap graph based distributed scheme to improve scheduling scalability concerning schedulability, scheduling efficiency, and latency and jitter. The distributed framework is established with the pipeline-parallelism pattern and verified superior in scalability. It first incorporates the deterministic feature into the distributed TSN configuration standard. Under this, specific scheduling is refined by building a so-called flow-overlap graph that efficiently characterizes flow-based scheduling features and further designing a hierarchical scheduling algorithm GFD. This scheme Pareto dominates the three scalability criteria theoretically and simulatively.

Roadside three-dimensional (3-D) object detection is essential for enhancing blind-less perception performance in cooperative autonomous driving. Current research has preliminarily explored the representations from different perspectives and constraints inside individuals. However, the accuracy of existing representations is hardly guaranteed under the wide-range conditions on roadside applications, and the constraints involving multiple targets are less considered. To address these, an accurate representation modeling and interindividual constraint-learning method is proposed. In representation modeling, the deficiencies of existing distance representations are systematically analyzed, and the relative depth is developed with the consideration of numerical distribution and error tendency under wide-range conditions. Besides, the limitation of existing reference-pixel representation is addressed by introducing Affine–Gaussian heatmaps, which accurately selects reference pixels and depresses extra responses based on geometric discrepancies. In constraint learning, the interindividual constraints are effectively extracted in the proposed graph-based module, which introduces powerful graph attention operations and a special designed implicit gradient flow to induce constraints into image feature maps. Extensive experiments on DAIR-V2X-I and Rope3-D demonstrate that significant improvements are achieved compared with concurrent state-of-arts on both the trained scenarios and unseen scenarios.

In industrial sites, multiple real-time control systems often share computing resources. However, burst computing tasks may lead to the random dropping of control computing subtasks, resulting in control failures and potential hazards. To address this issue, we propose an energy-efficient safety-aware task scheduling scheme based on mixed-integer programming. When burst computing tasks are triggered, this scheduling scheme adaptively releases resources from low-criticality control computing sub tasks and adjusts the processor speed based on the dynamic voltage and frequency scaling technology (DVFS), ensuring the timely completion of burst computing tasks and keeping the control system state deviation within a safe threshold. To achieve the scheduling scheme, we propose an efficient algorithm called EESASA. Simulation results show that EESASA can minimize the overall cost of control and processor energy while ensuring the safety of the control system and the timely completion of burst computing tasks.

In the era of Industry 4.0, the execution of intelligent industrial applications relies on collaborations among multi-type devices, such as sensing, computing, and control devices. Al-though a universal information model allows for integrated device management, the model-building complexity rises dramatically with increasing system functions. To address this challenge, an integrated information model with hierarchical architecture is designed. By decoupling device functions, a separated rule is adopted for model construction such that the information model of each device only contains function-related nodes and common attributes for describing device features, reducing the complexity of information model construction. Then, an aggregation server is constructed, enabling application-oriented views. Based on this, efficient management is facilitated by displaying management information of corresponding applications in the user interface, reducing the complexity of integration of sensing, computing, and control devices. Finally, experimental results demonstrate the effectiveness of the proposed scheme. Compared to the standard OPC UA information model, in the aggregation server, the number of model nodes of each type of devices in the application-oriented view is reduced by 79.8% on average.

The development of Industrial Internet of Things necessitates deterministic transmission of hybrid traffic with varying real-time requirements. Time-Sensitive Networking offers schemes combining scheduling mechanisms like the Time-Aware Shaper (TAS) and Cyclic Queuing and Forwarding (CQF). Current methods utilize the combination of TAS&CQF to schedule Time-Triggered (TT) and Audio-Video Bridging (AVB) traffic under corresponding mechanisms, respectively. However, the prior TT traffic orchestration restricts the scheduling solution space of AVB traffic, decreasing the effectiveness of combination and finally resulting in low schedulability. In this paper, we focus on enhancing the schedulability of TT&AVB scheduling by integrating TAS and Cyclic Specified Queuing and Forwarding (CSQF), which brings larger scheduling solution space to AVB traffic. The integration of TAS&CSQF is proposed by analyzing the impact of TAS on CSQF to expand the allocatable resource for AVB traffic. Then TAS&CSQF scheduling model is formulated to ensure deterministic requirements. Within this model, Timeslot Clustering Optimization (TCO) is proposed to optimize the scheduling solution space of AVB traffic and slice timeslot by refining the scheduling of TAS. Based on TCO, Flow Congestion Metric (FCM) is designed to improve schedulability by the congestion level of each link. An FCM-based algorithm is further presented to generate TT&AVB solutions incrementally. Simulation results demonstrate that our method reduces scheduling time cost by over 168 times and improves schedulability by 32% for 3000 flows compared to existing methods.

Semantic segmentation of large-scale outdoor point cloud captured by light detection and ranging (LiDAR) sensors can provide fine-grain and stereoscopic comprehension for the surrounding environment. However, limited by the receptive field of convolution kernel and ignoration of specific spatial properties inherent to the large-scale outdoor point cloud, the existing advanced LiDAR semantic segmentation methods inevitably abandon the unique radial long-range topological relationships. To this end, from the LiDAR perspective, we propose a novel Radial Transformer that can naturally and efficiently exploit the radial long-range dependencies exclusive to the outdoor point cloud for accurate LiDAR semantic segmentation. Specifically, we first develop a radial window partition to generate a series of candidate point sequences and then construct the long-range interactions among the densely continuous point sequences by the self-attention mechanism. Moreover, considering the varying-distance distribution of point cloud in 3-D space, a spatial-adaptive position encoding is particularly designed to elaborate the relative position. Furthermore, we fusion radial balanced attention for a better structure representation of real-world scenes and distant points. Extensive experiments demonstrate the effectiveness and superiority of our method, which achieves 67.5% and 77.7% mean intersection-over-union (mIoU) on two recognized large-scale outdoor LiDAR point cloud datasets SemanticKITTI and nuScenes, respectively.

The increasing scale of industrial production is leading to a greater demand for communication and computing capabilities, thereby increasing the likelihood of resource competition and conflict. This can cause stochastic overall task latency (including communication and computing latency), resulting in the occurrence of overdue tasks. To guarantee deterministic delays, the integration of edge computing (EC) with time-sensitive networking (TSN) emerges as a promising technology. However, the deterministic feature of TSN increases vulnerabilities to attacks within this integration. Particularly, uncertain denial-of-service (DoS) attacks can exhaust system resources and disrupt determinacy, causing prolonged delays, or communication failures. To this end, this article proposes an attack-tolerant TSN-based edge computing (TSN-EC) architecture to guarantee task determinacy. Based on the architecture, a task-level no-wait scheduling mechanism of TSN is proposed under packet switching mode, which ensures deterministic communication delays. A robust and deterministic task offloading scheduling (RDTOS) strategy is developed to minimize the number of overdue tasks by identifying the worst-case scenario of uncertain DoS attacks, considering each task's importance. To reduce computational complexity, a two-layer decomposition algorithm is proposed by further decomposing the master problem of the conventional C-CG algorithm. Experimental results conducted on a TSN-EC testbed demonstrate the superiority of the RDTOS strategy in enhancing security and providing overall task determinacy compared to related algorithms.

In intelligent factories, multiple industrial cameras capture continuous videos and upload them to edge nodes for automatic preinspection. For reliability, video chunks with low preinspection accuracy must be delivered to quality inspectors for manual reinspection. Video edge caching is an urgent technology for fast and efficient manual reinspection. However, time-varying and constrained industrial network conditions cannot meet the increasing demand for video-oriented quality reinspection. This article proposes a reinspection necessity-based video collaborative edge caching method, called Reine, utilizing video superresolution (VSR) for industrial quality reinspection. First, a video edge collaborative caching framework is established for industrial quality reinspection. Second, a reinspection necessity metric is designed, and a video edge caching strategy based on VSR benefit is proposed for edge nodes. Third, an NP-hard integer nonlinear programming problem is formulated for collaborative video caching and adaptive bitrate decisions. Simulation validates Reine outperforms the state-of-the-art video edge caching methods.

With the rapid development of Industrial Internet of Things (IIoT), time-sensitive networking (TSN) with deterministic and real-time features has gained broad interest. However, most existing research focuses on the network scheduling with fixed task placement and computing resource allocation, restricting the scheduling space of coupled task-network. To tackle this coupling problem, an efficient task-network scheduling (ETNS) scheme is proposed in this article for TSN. A task-conflict metric (TCM) is established to quantify the competition degree of scheduling resources. For increasing the overall scheduling space, a TCM-aware prescheduling method is proposed by optimizing task placement and routing paths to reduce the potential conflicts between tasks. Integrated with the prescheduling method, we design a TCM-aware parallel group-scheduling algorithm by reducing the conflicts between task groups to enhance schedulability and scalability. Experiments show that our ETNS scheme significantly improves the schedulability and scalability performances compared with the existing scheduling approaches. The larger the number of tasks, the higher the performance improvement.

Driven by the demand of Industry 4.0, the integration of 5G and time-sensitive networking (TSN) is proposed to provide ubiquitous connection and deterministic transmission. However, the heterogeneous access mechanisms and scheduling resolutions between 5G and TSN make it still intractable to schedule 5G and TSN resources jointly. To address this issue, we develop the network function virtualization-enabled 5G-TSN framework to offer unified resource management, where flows are scheduled by network slicing and virtual network function embedding, respectively. Specifically, a novel full-path age of information (FP-AoI) model is proposed as a new metric of the 5G-TSN integrated scheduling by innovatively encapsulating the 5G system as the sampling process of the virtual TSN network. To tackle the long latency tail brought by 5G, the 5G and TSN scheduling is formulated by a risk-aware FP-AoI minimization problem. Then, a decomposition and augmentation-based joint scheduling (DAS) algorithm is proposed to solve this NP-hard problem by decomposing it into three subproblems. The first two subproblems are proved to be convex. For the third subproblem, i.e., TSN scheduling, a FP-AoI-driven TSN scheduling scheme (FvQI) is designed by constructing an augmented logical topology according to constraints of service function chain and TSN characteristics. It realizes the TSN scheduling with low complexity. Simulation results demonstrate that our algorithms offer higher reliability, efficiency, and service acceptance ratio than benchmarks. Moreover, the DAS algorithm achieves a better tradeoff between the performance of time cost and AoI violation ratio with a small optimality gap.

In large-scale long-term dynamic environments, high-frequency dynamic objects inevitably lead to significant changes in the appearance of the scene at the same location at different times, which is catastrophic for place recognition (PR). Therefore, how to eliminate the influence of dynamic objects to achieve robust PR has universal practical value for mobile robots and autonomous vehicles. To this end, we suggest a novel semantically consistent LiDAR PR method based on chained cascade network, called SC_LPR, which mainly consists of a LiDAR semantic image inpainting network (LSI-Net) and a semantic pyramid Transformer-based PR network (SPT-Net). Specifically, LSI-Net is a coarse-to-fine generative adversarial network (GAN) with a gated convolutional autoencoder as the backbone. To effectively address the challenges posed by variable-scale dynamic object masks, we integrate the updated Transformer block with mask attention and gated trident block into LSI-Net. Sequentially, in order to generate a discriminative global descriptor representing the point cloud, we design an encoder with pyramid Transformer block to efficiently encode long-range dependencies and global contexts between different categories in the inpainted semantic image, followed by an augmented NetVALD, a generalized VLAD (Vector of Locally Aggregated Descriptors) layer that adaptively aggregates salient local features. Last but not least, we first attempt to create a LiDAR semantic inpainting dataset, called LSI-Dataset, to effectively validate the proposed method. Experimental comparisons show that our method not only improves semantic inpainting performance by about 6%, but also improves PR performance in dynamic environments by about 8% compared to the representative optimal baseline. LSI-Dataset will be publicly available at https://github.KD.LPR.com/.

The dynamic interaction among Connected and Automated Vehicles (CAVs) is becoming increasingly complex, encompassing factors such as dynamic topology and the dynamic states of multiple CAVs. Existing cooperative control methods struggle to explicitly represent dynamic interaction, which can lead to dangerous behavior, severe congestion, and even accidents. In this paper, we propose a cooperative control methodology that aims to improve safety and efficiency in the merging zone by deeply representing dynamic interaction among multiple CAVs. Our proposed methodology, named GMA-DRL, utilizes a spatial graph convolutional encoder with a multi-head attention mechanism to explicitly represent dynamic interaction among vehicles. Furthermore, deep reinforcement learning based on Actor-Critic with temporal relation regularization is utilized to ensure the consistency of dynamic interaction and generate cooperative driving actions for multiple CAVs. The GMA-DRL is tested in a series of typical merging scenarios with dynamic interaction. Extensive experimental results show that the GMA-DRL outperforms the existing cooperative control models in term of headway, average speed and acceleration. It demonstrates that the GMA-DRL with explicitly represent dynamic interaction can improve safety and efficiency of multiple CAVs in the merging zone.

Industrial Time-Sensitive Networking (TSN) provides deterministic mechanisms for real-time and reliable flow transmission. Increasing attention has been paid to efficient scheduling for time-sensitive flows with stringent requirements such as ultra-low latency and jitter. In TSN, the fine-grained traffic shaping protocol, cyclic queuing and forwarding (CQF), eliminates uncertain delay and frame loss via traffic timing in and out of queues. However, it inevitably causes high scheduling complexity. Moreover, complexity is quite sensitive to flow attributes and network scale. The problem stems in part from the lack of an attribute mining mechanism in existing frame-based scheduling. For time-critical industrial networks with large-scale complex flows, a so-called hyper-flow graph based scheduling scheme is proposed to improve the scheduling scalability in terms of schedulability, scheduling efficiency and latency & jitter. The hyper-flow graph is built by aggregating similar flow sets as hyper-flow nodes and designing a hierarchical scheduling framework. The flow attribute-sensitive scheduling information is embedded into the condensed maximal cliques, and reverse maps them precisely to congestion flow portions for re-scheduling. Its parallel scheduling reduces network scale induced complexity. Further, this scheme is designed in its entirety as a comprehensive scheduling algorithm GH2. It improves the three criteria of scalability along a Pareto front. Extensive simulation studies demonstrate its superiority. Notably, GH2 is verified its scheduling stability with a runtime of less than 100 ms for 1000 flows and near 1/190 of the SOTA FITS method for 3000 flows.

The joint design of control and transmission has been demonstrated to be a successful technique for enhancing the performance of industrial cyber-physical systems (ICPS). In the majority of existing works, the control cost and the transmission cost are defined independently, followed by a weighted total calculation. This approach suffers from a dimension consistency issue, leading the results to diverge from the system's actual optimal performance. Hence, it is necessary to consider the overall information of the loop and characterize the coupling relationship between control and transmission to construct the overall system performance function. This paper proposes a full loop age of information (FL-AoI) based control and transmission joint design architecture for multi-subsystem ICPS integrating multi-hop network. The state delay, input delay, and event trigger are all taken into consideration by FL-AoI to more fully portray the freshness of the information. We provide a novel control performance based on FL-AoI where the network characteristics are incorporated into the control cost, which could tackle the dimensionality mismatch brought by the form of weighted summation of the control and transmission cost. We also provide the FL-AoI-based strategy for the controller and event-triggering mechanism and derive the cost's boundary. The evaluation results demonstrate that, in comparison to the conventional joint design strategy, our solution increases the stability of the control system while decreasing the network burden.

Place recognition plays a crucial role in simultaneous localization and mapping. Unfortunately, however, changes in viewpoints and conditions in large-scale environments impose tricky challenges for PR. To this end, this article specifically proposes an explicit points-of-interest driven PR method, which consists of a road segmentation module based on grid-wise patch U-transformer and a PR module based on regions of interest siamese transformer NetVLAD (RI_STV). Especially for RI_STV, in the individual dimension, it is dedicated to exploring the local topological features of nonroad regions of interest. In the spatial dimension, an improved Transformer is introduced to capture the global interactions between features of interest. In the cluster dimension, NetVLAD embedded with weighted pooling is created to perform weighted aggregation of feature clusters to generate discriminative and general descriptors. Evaluation on various datasets shows that our customized method is not only impressively competitive, but also strikes the best balance between accuracy and real-time performance.

For improving the performance of industrial cyber-physical systems (ICPS), the joint design of control and transmission has been demonstrated as an efficient mechanism. However, the existing metrics in recent joint design works lack completeness and accuracy, which leads to the challenge of improving the stability and network resource utilization of ICPS. This article proposes a full-loop age of information (FL-AoI)-based control and transmission joint design architecture for multisubsystem ICPS integrating multihop network. The FL-AoI depicts the timeliness of information by state delay, input delay, and event-triggered status in full-loop ICPS. To avoid the instability caused by the input delay, we design a linear-quadratic regulator (LQR)-based controller by the FL-AoI and derive a feasible region of the FL-AoI for guaranteeing the stability of control systems. To ensure the accuracy of FL-AoI, we propose a routing and scheduling policy based on time-sensitive networking (TSN) for the deterministic bound of delay. Finally, we propose an optimal event-triggered policy based on FL-AoI for minimizing the data transmission amount while ensuring the system stability. The evaluation results show that our strategy improves the nonlinear and nonscalar control systems' stability while reducing the network burden of TSN compared with the traditional joint design strategies.

Object detection is crucial for surveillance in edge-enabled Industrial Internet-of-Things. Massive high-dimensional video streams without considering priority differences connect to edges via narrow and time-varying uplink channels, which should be analyzed efficiently for accurate and fast surveillance responses. However, time-varying network environments and constrained edge resources degrade surveillance's accuracy and real-time performance. This article proposes EdgeLeague for multiple video streams with different quality of service, which maintains high surveillance performance under edge resource limitations and uplink bandwidth dynamics by edge collaboration and camera network configuration. The EdgeLeague scheme is formulated by an NP-hard integer nonlinear problem to dynamically configure camera network resolutions and detection models on cooperative edges. To accelerate configuration responses, the formulated problem is decomposed into edge league grouping, video-league matching, and video configuration, solved by low-complexity algorithms. Theoretical analysis is provided for optimal video-league matching. Simulations show EdgeLeague achieves 0.312 s latency and 86.3% surveillance accuracy.

360$^\circ$video becomes increasingly attractive in smart factories due to its immersive experience for industrial surveillance. However, transmitting this kind of video requires a fairly large demand on the bandwidth due to its high-resolution and panoramic view. Moreover, low-latency responses of the video to users' head movements are required. This leads to the tradeoff between high video quality and low-latency response under limited bandwidth in factories. This article proposes a perception-sensitivity (PS)-based 360$^\circ$tiled video streaming method called PSTile for industrial surveillance. Specifically, a PS tiling strategy is constructed for valid tile grouping based on the designed PS index. Then, a tile bitrate adaptation problem is formulated to allocate bitrates to valid tiles. It jointly optimizes surveillance accuracy, end-to-end latency, and quality-of-experience of users under accuracy, latency, and bandwidth constraints. Simulations demonstrate that PSTile achieves at least 32.6% lower end-to-end latency and 19.3% higher average video bitrate than grid-tiling and clus-tiling methods.

Driven by the coexisted heterogeneous communication protocols and diverse quality of service (QoS) requirements of industrial applications, time-sensitive networking (TSN) has been proposed as a promising and unified standard to provide deterministic transmission. However, the traffic scheduling of the TSN network should be orchestrated in a coordinated manner, which is challenging to respond to dynamic applications rapidly. For this, network function virtualization (NFV) has been introduced to eliminate the tight coupling between functions and devices, thus enabling a more flexible network resource allocation. However, NFV cannot be simply applied in a TSN network due to the inherent complex characteristics of TSN. To address this issue, we develop SvTI, a service function chain (SFC) driven queue injection scheme in the NFV-enabled TSN network. The basic idea of SvTI is to jointly model virtual network functions (VNFs) embedding and the TSN multi-queue characteristic by constructing an ordered augmented topology according to the SFC. Thus, the VNF embedding and TSN queue injection problem can be transformed into a shortest path routing problem. Besides, considering the QoS requirements of applications, a TSN queue-based topology division mechanism is proposed to simplify the augmented topology further and improve the algorithm efficiency. Simulation results show that our SvTI obtains a smaller graph size than other works and is more scalable.

The development of the Industrial Internet of Things (1IoT) has given rise to massive information from the networked controllers, sensors and actuators, leading to the increasing demands for real-time and reliable transmission. Time-Sensitive Networking (TSN) provides the deterministic mechanism guar-antee for these demands, but with an open scheduling problem. For the low-latency and low-jitter traffic, it is hard to schedule in a scalable way, that is, increasing the scheduling speed under the Quality-of-Service (QoS) requirements. Therefore, this paper constructs a no-wait forwarding (NW-TAS) model with a time-aware shaper to eliminate the queuing delay and jitter, and further converts it into a flow-aware model by divisibility theory for scheduling simplification. With the converted model, an interval transformation-based method is proposed to get the analytical expression of feasible scheduling for each flow. Then, a flow-aware NW- TAS scheduling algorithm (FANS) with cyclic interval searching is designed to compress invalid search spaces. The evaluation results show that our method decreases the transmission latency of 1000 flows by more than 23 % while increasing the scheduling speed by 43x than the existing works.

The interoperability of heterogeneous networks, including hybrid industrial wired/wireless protocols, is a vital aspect of the Industrial Internet of Things (IIoT) since various industrial protocols have coexisted. Therefore, it is hard to obtain a multiple protocol conversion solution with the flexible configuration. Moreover, the previous works do not adapt to the Time Sensitive Networking (TSN), which is considered as the potential technology of IIoT. To tackle the above problems, we proposed an architecture of the multiple conversion system supporting the conversion of multiple protocols. Then, we proposed a protocol conversion mechanism to improve the flexibility of multiple protocol conversion by separating into data and configuration planes. Moreover, we propose a TSN-compatible frame with dynamic priority mapping algorithm, which adjusts the priority in the VLAN tag by the processing delay. Finally, we develop a hardware module and system supporting multiple protocol conversion, which verify that the proposed architecture could satisfy the flexible conversion requirement through the experiments.

Cloud manufacturing aims to carry out large-scale collaborative production through remote equipment management. To improve management efficiency, it is necessary to construct a unified information model and an adaptive communication framework for manufacturing lines with heterogeneous (high reliable/ low load) needs. OPC UA has become a prominent solution for remote configuration with extensible information models and various transport mechanisms. However, the existing solutions based on OPC UA focus on the information model and communication framework for the machine level, which is hard to support efficient remote management of the production line. In this paper, we construct the model of the process and parameter information in production-line level with a unified manner, which enables unified scheduling, configuration, and monitoring. The operational data are modeled hierarchically to reduce the amount of data transmission during monitoring. The hybrid communication framework is designed by integrating the Client-Server and PubSub models with edge assistance, which is to meet the heterogeneous communication requirements. We implement the management architecture on the physical platform to verify the performance. The experiments show that our architecture is suitable for remote configuration in terms of the combined performance of packet loss rate and CPU load with a massive connection.

To improve the performance of industrial cyber-physical systems (ICPS), the joint design of control and transmission has been shown to be an effective mechanism. However, the existing joint design work lack completeness and accuracy, which brings challenges to improving the stability and network resource utilization of ICPS. In this paper, we propose a control and transmission joint design architecture for integrated multi-subsystem ICPS for multi-hop networks. We consider the timeliness of information through state delays, input delays, and event-triggered states in ICPS. To avoid the instability caused by input delay, we design an LQR-based controller and derive the feasible region of delay to guarantee the stability of the control system. Finally, we propose an event-triggered strategy that represents control and transmission costs to minimize the amount of data transfer while ensuring system stability. The evaluation results show that our strategy improves the stability of the control system while reducing the network burden compared with the traditional joint design method.

As the global industrial upgrading requires higher reliability and real-time performance of data communication, Time-sensitive Networking (TSN) has been widely studied. Al-though many TSN scheduling algorithms are designed, there is no standardized analysis report after scheduling and comprehensive scheduling performance evaluation. This paper presents a complete automatic report generation system to analyze the scheduling performance. To standardize various data in TSN-based manufacturing, a uniform auto-generated report model is defined based on the Open Platform Communication Unified Architecture (OPC UA). A learning-based performance evaluation (LPE) method is established to comprehensively analyze the performance of TSN scheduling. In LPE, analytical hierarchy process (AHP) and entropy weight method (EWM) is adopted to optimize the weight distribution of performance indexes objectively, and convolutional neural network (CNN) is used to get the final evaluation result rapidly. Compared with the previous evaluation methods, simulations show the training time of the evaluation method is significantly reduced.

Co-design of control and communication is critical to enhancing the control performance of industrial Cyber-Physical System (ICPS). However, the stochastic features of non-deterministic communication strategies in existing works limit control performance improvement. This paper proposes a centralized-control and deterministic-transmission co-design architecture for multi-subsystem ICPS over Time-Sensitive Network (TSN). Packet-wise no-wait transmission scheduling is devised to enable fine-grained scheduling for deterministic delays of the control system data. An integrated system model for the co-design architecture is constructed by integrating scheduling variables into the control system model, which enables simultaneous optimization of the control and transmission strategies for improving the feasible solution space and control performance. Co-design problem based on the integrated model is formulated as mixed-integer non-linear programming (MINLP) problem. A Tabu-search-based heuristic algorithm is proposed to obtain near-optimal solutions efficiently for the co-design problem. Simulation results demonstrate that the proposed method effectively improves control performance compared with best-effort transmission without co-design.

Multiobject tracking (MOT) is a crucial technology for security surveillance, which is computationally intensive due to the requirement of processing a large number of video streams within low latency in practice. The input video streams of MOT are processed on a cloud computing center with abundant computational capability, posing heavy pressures on delivering video streams to the cloud. Recent advances in the Internet-of-Things (IoT) technology provide edge-computing-based solutions for video analytics at scale. However, the gap between MOT’s high computational capability demand and IoT devices’ resource-constrained nature remains significant. In this article, a resource-efficient MOT (REMOT) method is proposed for real-time surveillance on IoT embedded devices, including an affinity measurement based on an appearance model with angular triplet loss and a motion association that substitutes the time-consuming graph-based data association stage. Considering the tradeoff between latency and accuracy, we design an optimization strategy on the parallel processing of deep learning models’ layers to accelerate the inference speed with less accuracy loss. Besides, we employ a model compression strategy for model size reduction. Experiments on MOT16 and MOT17 benchmarks demonstrate that REMOT reduces 2.4$\times $latency compared with the original implementation and achieves a running speed of 81 frames per second (fps) on an embedded device with only a marginal accuracy loss (6%), which meets the requirements of real-time processing and low-latency response for surveillance.

The deterministic and real-time communication is the indispensable requirement in Industrial Internet of Things (IIoT) application areas. Time-sensitive networking (TSN) is a promising technology for this kind of communication demands through designing proper scheduling and routing mechanisms. However, it is still challenging to design the mechanisms for large-scale instances due to high computational complexity. In order to guarantee schedulability and scalability, a learning-based scalable scheduling and routing co-design (LSSR) architecture is proposed in this article for TSN. A stream partition method combining classification and graph-based clustering is established to reduce interpartition conflicts to enhance schedulability based on the explored domain knowledge and the characterized stream data set for practical requirements. Integrated with the stream partition method, we construct the constraints of scheduling and routing co-design to guarantee the deterministic and real-time transmission. An iterative scheduling algorithm is proposed to reduce the computational complexity and thus, to enhance scalability. Simulations demonstrate the effectiveness and advantages of the proposed LSSR scheme.

As an emerging communication technology, time-sensitive networking (TSN) promises the real time and deterministic interaction of massive data in Industrial Internet of Things. However, it is challenging to schedule the time-sensitive flows timely and superiorly through the mechanism analysis for current TSN scheduling models, especially in complex industrial scenarios. In this article, we propose an analysis approach of flow sequences based on divisibility theory to characterize the flow conflicts and dependencies, which derives the scheduling flexibility based on flow position diversity (PD) and the equivalent flow judgment conditions for slot occupancy. Integrating the abovementioned derivation, a parallel computing framework with the generalized slot length is established to lower the scheduling complexity. Within each computing unit, an incremental scheduling algorithm with the flow judgment conditions and PD-based search boundary is proposed. It reduces the scheduling complexity further while maintaining load balance for the mixed transmission of periodic and aperiodic flows. To achieve the optimality of runtime and load balance, two PD-based flow sorting strategies are designed, respectively. The evaluation results show that compared with the existing works, the runtime efficiency of scheduling at scale is increased by at least 1500 times in complex traffic scenarios while the load balance on the network links is also improved.

The safety and efficiency of the merging zone is particularly important for traffic networks. Although autonomous vehicle improves the safety and efficiency from vehicle view, traffic controlling in merging zone mostly focus on improving efficiency from roadside view. Lacking of detailed driving recommendation, it ignores the safety of merging zone where commercial vehicle pose a high collision risk in real traffic. This paper proposes a roadside decision-making methodology to simultaneously improve the safety and efficiency of merging zone. We have built two modules, namely assessment and decision-making. Assessment module takes advantage of Bayesian inference to evaluate dynamic collision risk. Decision-making module based on deep reinforcement learning recommends the actions to commercial vehicles by roadside unit. A series of typical simulation tests show that our method increases the TTC of commercial vehicles by an average of 62.7%. In the free flow, the overall travel time of vehicles in the merging zone is reduced by 11.68%. Most notably, when congestion occurred, the average jam length is reduced by 59.68% on the premise of safety. Moreover, the average accuracy of the roadside decision-making method on the evaluation metrics of TTC, travel time, and jam length are 93.73%, 91.65%, and 94.45%, respectively. The experimental results show that the roadside decision-making methodology simultaneously improves safety and efficiency, and it dynamically adapts free and congested traffic flow.

Driven by the advantages of the ubiquitous connection of 5G and the determinacy of Time-Sensitive Networking (TSN), the integration of 5G and TSN is expected to provide flexible and deterministic communications for the industry. However, due to the diverse quality of service (QoS) demands of industrial applications, it is challenging to provide suitable QoS mapping across industrial 5G-TSN networks and offer dynamic services via heterogeneous infrastructures. To address this issue, we design a QoS-aware dynamic data injection scheme to realize the interconnection between 5G and TSN under edge-assisted 5G-TSN architecture. To break the tight coupling between applications and infrastructures, we focus on the virtual network function (VNF) mapping problems to facilitate the QoS provisioning for different applications leveraging the network function virtualization (NFV) technique. We first formulate it as a mixed integer linear programming (MILP) with time-sensitive constraints. Then we develop PVMS, a preemption-based two-stage heuristic algorithm for VNF mapping and scheduling in the 5G-TSN network. In particular, we dynamically map the VNFs of arrived applications by greedily searching the earliest available 5G-TSN resources. To further meet the low-latency requirements, we employ a preemption mechanism to provide no-wait transmission for higher priority applications at the cost of the preempted applications being postponed. Simulation results demonstrate that the proposed PVMS has better performance in terms of the acceptance ratio, average delay, and QoS guarantee.

Precise time protocol is widely used to enable devices to have unified time in the industrial scene. Due to unknown delay asymmetry affecting the synchronization accuracy, numerous researches focus on parameter estimation methods for compensation. However, the fixed delay is difficult to determine in practical, and network dynamics aggravate delay asymmetry, which reduces the actual effect of synchronization. In this paper, a non-parametric estimation method is introduced into synchronization process modeling, which can fit the timestamp data well without fixed delay value. A double-layer clock synchronization method is proposed to estimate the clock skew and offset, where sparse support vector regression and stochastic gradient descent method are combined to improve the operational efficiency and adaptability to network dynamics. Simulation results based on actual measured data show that the proposed method has better performance in both static and dynamic networks than traditional methods.

Realtime and intelligent video surveillance via camera networks involve computation-intensive vision detection tasks with massive video data, which is crucial for safety in the edge-enabled industrial Internet of Things (IIoT). Multiple video streams compete for limited communication resources on the link between edge devices and camera networks, resulting in considerable communication congestion. It postpones the completion time and degrades the accuracy of vision detection tasks. Thus, achieving high accuracy of vision detection tasks under the communication constraints and vision task deadline constraints is challenging. Previous works focus on single camera configuration to balance the tradeoff between accuracy and processing time of detection tasks by setting video quality parameters. In this paper, an adaptive camera network self-configuration method (CANS) of video surveillance is proposed to cope with multiple video streams of heterogeneous quality of service (QoS) demands for edge-enabled IIoT. Moreover, it adapts to video content and network dynamics. Specifically, the tradeoff between two key performance metrics, i.e., accuracy and latency, is formulated as an NP-hard optimization problem with latency constraints. A low-complexity algorithm is proposed to solve the optimization problem based on greedy searching. Simulation on real-world surveillance datasets demonstrates that the proposed CANS method achieves low end-to-end latency (13 ms on average) with high accuracy (92%) with network dynamics, which validates its effectiveness.

Time-Sensitive Networking (TSN) is a series of standards designed to enhance reliable and real-time transmission. Switching architecture is the essential component in TSN switches to guarantee the different quality of service (QoS) requirements. However, most existing TSN switching architectures are based on the fixed queue scheduling such as Input Queue or Output Queue, which leads to complex schedule processes and inefficient memory utilization. Therefore, a flexible and efficient switching architecture is needed in terms of heterogeneous traffics requirements. This paper proposes a Virtual-Queue Switching (VQS) architecture with Parallel Shared Memory (PSM) for TSN switches. First, we develop a virtual queue scheduler using the queue ID and the flow rank. By configuring the queue ID and the flow rank, the VQS architecture supports multiple scheduling strategies. Second, parallel shared memory (PSM) management is designed to ensure that storage of TS flows takes precedence over other flows. All kinds of flows share storage resources in PSM, which improves memory utilization. At last, a scheduling algorithm for IEEE 802.1Qbv based on VQS architecture is designed. Compared From the comparison results with the previous switching

Reliable estimation of vehicle lateral position plays an essential role in enhancing the safety of autonomous vehicles. However, it remains a challenging problem due to the frequently occurred road occlusion and the unreliability of employed reference objects (e.g., lane markings, curbs, etc.). Most existing works can only solve part of the problem, resulting in unsatisfactory performance. This paper proposes a novel deep inference network (DINet) to estimate vehicle lateral position, which can adequately address the challenges. DINet integrates three deep neural network (DNN)-based components in a human-like manner. A road area detection and occluding object segmentation (RADOOS) model focuses on detecting road areas and segmenting occluding objects on the road. A road area reconstruction (RAR) model tries to reconstruct the corrupted road area to a complete one as realistic as possible, by inferring missing road regions conditioned on the occluding objects segmented before. A lateral position estimator (LPE) model estimates the position from the reconstructed road area. To verify the effectiveness of DINet, road-test experiments were carried out in the scenarios with different degrees of occlusion. The experimental results demonstrate that DINet can obtain reliable and accurate (centimeter-level) lateral position even in severe road occlusion.

As an emerging communication tool, Time-Sensitive Networking (TSN) is proposed by the IEEE 802.1 TSN Task Group to achieve deterministic data transmission. TSN defines protocols to ensure the determinism of traditional Ethernet by configuring gate control list (GCL). However, calculating schedules of GCL according to different time-sensitive applications, is not well-defined in the standard. In this paper, we focus on the problem of mixed time-sensitive data transmission. To this end, we first model the data into three categories: high time-sensitive (HTS) flows, low time-sensitive (LTS) flows, and best-effort flows. Then based on the models, we propose a coordinated transmission framework to transmit mixed time-sensitive data. Under this framework, we develop a parameter selection approach for choosing the proper cycle time and the scheduling unit. To reduce the impact of HTS data on LTS data flows, we formulate a fine-grained scheduling problem. Then, we design an injection time grouping (ITG) algorithm by grouping the flows with the same period to reduce the computation complexity. Simulation results corroborate the effectiveness of the parameter selection approach and ITG algorithm.

Modern Industrial Internet-of-Things (IIoT) requires reliable interaction and integration of data in the network. Thus, time sensitive networking (TSN) is a promising technology due to deterministic latency guarantee mechanisms for data transmission. However, the multiple mechanisms are based on the networkwide precise time synchronization. In this paper, to achieve precise and reliable clock synchronization of TSN, we propose a hierarchical timing-frequency synchronization mechanism. Specifically, the network is divided into two layers according to the network clock synchronization function. The top layer adopts tree-based synchronization to provide a global clock and an interface with external standard clock synchronization, and the underlying one adopts a distributed synchronization protocol to improve the reliability, which obtains the reference clock by multiple nodes to avoid the single point of failure. To improve synchronization efficiency, a time-frequency fusion synchronization mechanism is proposed, which comprehensively considers the synchronization time slot difference and the time-frequency coupling relationship to improve the synchronization speed under the same synchronization period. Simulation results show that the proposed synchronization mechanism has higher synchronization efficiency than the traditional methods, and improves the clock synchronization speed and accuracy significantly.

The enhanced digital map is of great significance for various Intelligent Transportation System (ITS) applications and services, especially at the lane-level. This requirement motives the development of road modeling in the enhanced digital map at the lane-level. However, previous enhanced digital maps do not provide detailed modeling of special intersections which are covered by vegetation in the central region. In this paper we propose a novel lane-level road model for this special intersection scenario. The proposed intersection model can be considered into two levels: topological structure and geometrical structure. Topological structure of this model helps describe the connectivity, turn restrictions and other attributes of the special intersection in the real world. Geometrical structure of this model helps describe the virtual lanes of the internal part of the special intersection using cardinal spline, which better approximates the real vehicle trajectory at the intersection. The proposed intersection model has been verified and evaluated through experiments. The results demonstrate the effectiveness of the proposed intersection model in representing the lane-level topological and geometrical details of special intersection which is covered by vegetation in its central region.

In this paper, we propose a reliable hybrid positioning methodology by combining the advantages of H∞filter and extreme learning machine (ELM), which addresses GPS outages and uncertain nonlinear drift of MEMS INS simultaneously. A novel parallel-dual-H∞filtering (PDHF) mechanism is proposed to prevent the H∞filter from diverging during GPS outages and to make full use of supplementary observations. The PDHF is composed of an enhanced H∞filter and an auxiliary H∞filter. The enhanced H∞filter is developed by fusing not only GPS information but also supplementary observations, which include yaw angle provided by electronic compass, longitudinal velocity derived from wheel speed sensor, and lateral velocity constrained by assumptions, whereas the auxiliary H∞filter only fuses the supplementary observations. Furthermore, an ELM module with good generalization ability is designed and augmented with the auxiliary H∞filter to constitute a “virtual enhanced H∞filter.” In the case of GPS outages, the “virtual enhanced H∞filter” provides accurate corrections for stand-alone INS. Due to the characteristics of the Hoc filter, the proposed methodology is immune to uncertain nonlinear drift of MEMS INS in nature. To verify the effectiveness of the proposed methodology, road-test experiments with various scenarios were performed. The experimental results indicate that the proposed methodology outperform all the compared counterparts.