Yuanqing Xia

Kun Liu, Emilia Fridman, Karl Henrik Johansson et al.

The Jensen inequality has been recognized as a powerful tool to deal with the stability of time-delay systems. Recently, a new inequality that encompasses the Jensen inequality was proposed for the stability analysis of systems with finite delays. In this paper, we first present a generalized integral inequality and its double integral extension. It is shown how these inequalities can be applied to improve the stability result for linear continuous-time systems with gamma-distributed delays. Then, for the discrete-time counterpart we provide an extended Jensen summation inequality with infinite sequences, which leads to less conservative stability conditions for linear discrete-time systems with poisson-distributed delays. The improvements obtained thanks to the introduced generalized inequalities are demonstrated by examples.

Zhongqi Sun, Li Dai, Kun Liu et al.

In this paper, two robust model predictive control (MPC) schemes are proposed for tracking control of nonholonomic systems with bounded disturbances: tube-MPC and nominal robust MPC (NRMPC). In tube-MPC, the control signal consists of a control action and a nonlinear feedback law based on the deviation of the actual states from the states of a nominal system. It renders the actual trajectory within a tube centered along the optimal trajectory of the nominal system. Recursive feasibility and input-to-state stability are established and the constraints are ensured by tightening the input domain and the terminal region. While in NRMPC, an optimal control sequence is obtained by solving an optimization problem based on the current state, and the first portion of this sequence is applied to the real system in an open-loop manner during each sampling period. The state of nominal system model is updated by the actual state at each step, which provides additional a feedback. By introducing a robust state constraint and tightening the terminal region, recursive feasibility and input-to-state stability are guaranteed. Simulation results demonstrate the effectiveness of both strategies proposed.

Yuhan Suo, Runqi Chai, Kaiyuan Chen et al.

With the rapid development of the Internet of Things (IoT), the risks of data tampering and malicious information injection have intensified, making efficient threat detection in large-scale distributed sensor networks a pressing challenge. To address the decline in malicious information detection efficiency as network scale expands, this paper investigates a robust set partitioning strategy and, on this basis, develops a distributed attack detection framework with theoretical guarantees. Specifically, we introduce a gain mutual influence metric to characterize the inter-subset interference arising during gain updates, thereby revealing the fundamental reason for the performance gap between distributed and centralized algorithms. Building on this insight, the set partitioning strategy based on Grassmann distance is proposed, which significantly reduces the computational cost of gain updates while maintaining detection performance, and ensures that the distributed setting under subset partitioning preserves the same theoretical performance bound as the baseline algorithm. Unlike conventional clustering methods, the proposed set partitioning strategy leverages the intrinsic observational features of sensors for robust partitioning, thereby enhancing resilience to noise and interference. Simulation results demonstrate that the proposed method limits the performance gap between distributed and centralized detection to no more than 1.648$\%$, while the computational cost decreases at an order of $O(1/m)$ with the number of subsets $m$. Therefore, the proposed algorithm effectively reduces computational overhead while preserving detection accuracy, offering a practical low-cost and highly reliable security detection solution for edge nodes in large-scale IoT systems.

Tayyab Manzoor, Yasir Ali, Yuanqing Xia et al.

Autonomous aerial vehicles necessitate control strategies that balance computational efficiency with robust performance in dynamic operational environments. This paper proposes a model predictive control (MPC) framework for aerial platforms that leverages physics-informed machine learning (PIML) to achieve an optimal balance between computational tractability and robust performance. At the core of the proposed approach lies a sparse, control-affine model identified via the PIML method, which provides a parsimonious yet interpretable representation of the system dynamics by embedding first-principles knowledge and learning residual uncertainties from operational data. This model is incorporated within a robust MPC scheme that adopts a high-order Runge-Kutta discretization to ensure prediction accuracy and an adaptive tube-based mechanism to guarantee constraint satisfaction under uncertainty. The online adaptation of the tube, directly informed by the residual error of the PIML model, ensures robust stability without introducing excessive conservatism. Rigorous theoretical proofs are provided to establish recursive feasibility and stability. Numerical simulations and experiments on a quadrotor demonstrate that our method significantly reduces computational load compared to nonlinear MPC and robust MPC using a high-fidelity model, while outperforming PID, nonlinear MPC, neural-network-based MPC, and fixed-tube robust MPC in tracking performance and robustness, showcasing the practical efficiency of the proposed PIML-based control synthesis for resource-constrained aerial systems.

Kaiyuan Chen, Yuhan Suo, Shaowei Cui et al.

This paper addresses the problem of trajectory optimization for unmanned aerial vehicles (UAVs) performing time-sensitive medical deliveries in urban environments. Specifically, we consider a single UAV with 3 degree-of-freedom dynamics tasked with delivering blood packages to multiple hospitals, each with a predefined time window and priority. Mission objectives are encoded using Signal Temporal Logic (STL), enabling the formal specification of spatial-temporal constraints. To ensure safety, city buildings are modeled as 3D convex obstacles, and obstacle avoidance is handled through a Convex Feasible Set (CFS) method. The entire planning problem-combining UAV dynamics, STL satisfaction, and collision avoidance-is formulated as a convex optimization problem that ensures tractability and can be solved efficiently using standard convex programming techniques. Simulation results demonstrate that the proposed method generates dynamically feasible, collision-free trajectories that satisfy temporal mission goals, providing a scalable and reliable approach for autonomous UAV-based medical logistics.

Yuhan Suo, Senchun Chai, Xudong Zhao et al.

Distributed online learning in multi-agent systems is highly vulnerable to adversarial influence, especially when malicious agents cannot be fully isolated during the transient stage. While existing studies mainly pursue resilient consensus or secure fusion, they pay much less attention to the learning inefficiency and extra evolution cost accumulated during the defense process. This paper addresses this gap by developing a cost-aware distributed online learning framework with strict rejection behavior against adversarial agents.Under this mechanism, the state evolution cost of online adaptation is formulated and the cost amplification effect caused by adversarial interactions is theoretically characterized. To balance robustness, convergence efficiency, and long-term cost, we propose an adaptive adjustment mechanism for the state-evolution rate. The resulting outer-layer update can be equivalently viewed as a constrained online optimization problem. We further establish the well-posedness and regularity of the associated periodic Riccati layer, and show that the outer-layer update ensures feasibility and controlled variation. Based on these properties, closed-loop practical stability is rigorously established via a two-time-scale Lyapunov framework. Simulations demonstrate that the proposed method achieves robust and low-cost convergence under adversarial disturbances. Furthermore, a multi-satellite target tracking scenario with malicious interference further demonstrates the practical effectiveness of the strict rejection behavior.

Zigeng Yan, Di-Hua Zhai, Yuanqing Xia

Human motion prediction is an important and challenging task in many computer vision application domains. Recent work concentrates on utilizing the timing processing ability of recurrent neural networks (RNNs) to achieve smooth and reliable results in short-term prediction. However, as evidenced by previous work, RNNs suffer from errors accumulation, leading to unreliable results. In this paper, we propose a simple feed-forward deep neural network for motion prediction, which takes into account temporal smoothness and spatial dependencies between human body joints. We design a Multi-scale Spatio-temporal graph convolutional networks (GCNs) to implicitly establish the Spatio-temporal dependence in the process of human movement, where different scales fused dynamically during training. The entire model is suitable for all actions and follows a framework of encoder-decoder. The encoder consists of temporal GCNs to capture motion features between frames and semi-autonomous learned spatial GCNs to extract spatial structure among joint trajectories. The decoder uses temporal convolution networks (TCNs) to maintain its extensive ability. Extensive experiments show that our approach outperforms SOTA methods on the datasets of Human3.6M and CMU Mocap while only requiring much lesser parameters. Code will be available at https://github.com/yzg9353/DMSGCN.

Tijin Yan, Hongwei Zhang, Tong Zhou et al.

Multivariate time series prediction has attracted a lot of attention because of its wide applications such as intelligence transportation, AIOps. Generative models have achieved impressive results in time series modeling because they can model data distribution and take noise into consideration. However, many existing works can not be widely used because of the constraints of functional form of generative models or the sensitivity to hyperparameters. In this paper, we propose ScoreGrad, a multivariate probabilistic time series forecasting framework based on continuous energy-based generative models. ScoreGrad is composed of time series feature extraction module and conditional stochastic differential equation based score matching module. The prediction can be achieved by iteratively solving reverse-time SDE. To the best of our knowledge, ScoreGrad is the first continuous energy based generative model used for time series forecasting. Furthermore, ScoreGrad achieves state-of-the-art results on six real-world datasets. The impact of hyperparameters and sampler types on the performance are also explored. Code is available at https://github.com/yantijin/ScoreGradPred.

Tijin Yan, Hongwei Zhang, Zirui Li et al.

Representation learning over graph structure data has been widely studied due to its wide application prospects. However, previous methods mainly focus on static graphs while many real-world graphs evolve over time. Modeling such evolution is important for predicting properties of unseen networks. To resolve this challenge, we propose SGRNN, a novel neural architecture that applies stochastic latent variables to simultaneously capture the evolution in node attributes and topology. Specifically, deterministic states are separated from stochastic states in the iterative process to suppress mutual interference. With semi-implicit variational inference integrated to SGRNN, a non-Gaussian variational distribution is proposed to help further improve the performance. In addition, to alleviate KL-vanishing problem in SGRNN, a simple and interpretable structure is proposed based on the lower bound of KL-divergence. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed model. Code is available at https://github.com/StochasticGRNN/SGRNN.

Haosong Peng, Wei Feng, Hao Li et al.

The advent of edge computing has made real-time intelligent video analytics feasible. Previous works, based on traditional model architecture (e.g., CNN, RNN, etc.), employ various strategies to filter out non-region-of-interest content to minimize bandwidth and computation consumption but show inferior performance in adverse environments. Recently, visual foundation models based on transformers have shown great performance in adverse environments due to their amazing generalization capability. However, they require a large amount of computation power, which limits their applications in real-time intelligent video analytics. In this paper, we find visual foundation models like Vision Transformer (ViT) also have a dedicated acceleration mechanism for video analytics. To this end, we introduce Arena, an end-to-end edge-assisted video inference acceleration system based on ViT. We leverage the capability of ViT that can be accelerated through token pruning by only offloading and feeding Patches-of-Interest to the downstream models. Additionally, we design an adaptive keyframe inference switching algorithm tailored to different videos, capable of adapting to the current video content to jointly optimize accuracy and bandwidth. Through extensive experiments, our findings reveal that Arena can boost inference speeds by up to 1.58\(\times\) and 1.82\(\times\) on average while consuming only 47\% and 31\% of the bandwidth, respectively, all with high inference accuracy.

Sheng Yu, Di-Hua Zhai, Yuanqing Xia

While most current RGB-D-based category-level object pose estimation methods achieve strong performance, they face significant challenges in scenes lacking depth information. In this paper, we propose a novel category-level object pose estimation approach that relies solely on RGB images. This method enables accurate pose estimation in real-world scenarios without the need for depth data. Specifically, we design a transformer-based neural network for category-level object pose estimation, where the transformer is employed to predict and fuse the geometric features of the target object. To ensure that these predicted geometric features faithfully capture the object's geometry, we introduce a geometric feature-guided algorithm, which enhances the network's ability to effectively represent the object's geometric information. Finally, we utilize the RANSAC-PnP algorithm to compute the object's pose, addressing the challenges associated with variable object scales in pose estimation. Experimental results on benchmark datasets demonstrate that our approach is not only highly efficient but also achieves superior accuracy compared to previous RGB-based methods. These promising results offer a new perspective for advancing category-level object pose estimation using RGB images.

Haosong Peng, Tianyu Qi, Yufeng Zhan et al.

With the advancement of computer vision, the recently emerged 3D Gaussian Splatting (3DGS) has increasingly become a popular scene reconstruction algorithm due to its outstanding performance. Distributed 3DGS can efficiently utilize edge devices to directly train on the collected images, thereby offloading computational demands and enhancing efficiency. However, traditional distributed frameworks often overlook computational and communication challenges in real-world environments, hindering large-scale deployment and potentially posing privacy risks. In this paper, we propose Radiant, a hierarchical 3DGS algorithm designed for large-scale scene reconstruction that considers system heterogeneity, enhancing the model performance and training efficiency. Via extensive empirical study, we find that it is crucial to partition the regions for each edge appropriately and allocate varying camera positions to each device for image collection and training. The core of Radiant is partitioning regions based on heterogeneous environment information and allocating workloads to each device accordingly. Furthermore, we provide a 3DGS model aggregation algorithm that enhances the quality and ensures the continuity of models' boundaries. Finally, we develop a testbed, and experiments demonstrate that Radiant improved reconstruction quality by up to 25.7\% and reduced up to 79.6\% end-to-end latency.

Yongkang Wang, Dihua Zhai, Yufeng Zhan et al.

Federated learning (FL) is a distributed machine learning paradigm where enormous scattered clients (e.g. mobile devices or IoT devices) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data decentralized. Unfortunately, FL is susceptible to a variety of attacks, including backdoor attack, which is made substantially worse in the presence of malicious attackers. Most of algorithms usually assume that the malicious at tackers no more than benign clients or the data distribution is independent identically distribution (IID). However, no one knows the number of malicious attackers and the data distribution is usually non identically distribution (Non-IID). In this paper, we propose RFLBAT which utilizes principal component analysis (PCA) technique and Kmeans clustering algorithm to defend against backdoor attack. Our algorithm RFLBAT does not bound the number of backdoored attackers and the data distribution, and requires no auxiliary information outside of the learning process. We conduct extensive experiments including a variety of backdoor attack types. Experimental results demonstrate that RFLBAT outperforms the existing state-of-the-art algorithms and is able to resist various backdoor attack scenarios including different number of attackers (DNA), different Non-IID scenarios (DNS), different number of clients (DNC) and distributed backdoor attack (DBA).

Tijin Yan, Tong Zhou, Yufeng Zhan et al.

With the development of AIoT, data-driven attack detection methods for cyber-physical systems (CPSs) have attracted lots of attention. However, existing methods usually adopt tractable distributions to approximate data distributions, which are not suitable for complex systems. Besides, the correlation of the data in different channels does not attract sufficient attention. To address these issues, we use energy-based generative models, which are less restrictive on functional forms of the data distribution. In addition, graph neural networks are used to explicitly model the correlation of the data in different channels. In the end, we propose TFDPM, a general framework for attack detection tasks in CPSs. It simultaneously extracts temporal pattern and feature pattern given the historical data. Then extract features are sent to a conditional diffusion probabilistic model. Predicted values can be obtained with the conditional generative network and attacks are detected based on the difference between predicted values and observed values. In addition, to realize real-time detection, a conditional noise scheduling network is proposed to accelerate the prediction process. Experimental results show that TFDPM outperforms existing state-of-the-art attack detection methods. The noise scheduling network increases the detection speed by three times.

Hongwei Zhang, Weidong Zou, Hongbo Zhao et al.

Adaptive optimization methods have been widely used in deep learning. They scale the learning rates adaptively according to the past gradient, which has been shown to be effective to accelerate the convergence. However, they suffer from poor generalization performance compared with SGD. Recent studies point that smoothing exponential gradient noise leads to generalization degeneration phenomenon. Inspired by this, we propose AdaL, with a transformation on the original gradient. AdaL accelerates the convergence by amplifying the gradient in the early stage, as well as dampens the oscillation and stabilizes the optimization by shrinking the gradient later. Such modification alleviates the smoothness of gradient noise, which produces better generalization performance. We have theoretically proved the convergence of AdaL and demonstrated its effectiveness on several benchmarks.

Hongwei Zhang, Tijin Yan, Zenjun Xie et al.

Graph convolutional networks (GCNs) have achieved promising performance on various graph-based tasks. However they suffer from over-smoothing when stacking more layers. In this paper, we present a quantitative study on this observation and develop novel insights towards the deeper GCN. First, we interpret the current graph convolutional operations from an optimization perspective and argue that over-smoothing is mainly caused by the naive first-order approximation of the solution to the optimization problem. Subsequently, we introduce two metrics to measure the over-smoothing on node-level tasks. Specifically, we calculate the fraction of the pairwise distance between connected and disconnected nodes to the overall distance respectively. Based on our theoretical and empirical analysis, we establish a universal theoretical framework of GCN from an optimization perspective and derive a novel convolutional kernel named GCN+ which has lower parameter amount while relieving the over-smoothing inherently. Extensive experiments on real-world datasets demonstrate the superior performance of GCN+ over state-of-the-art baseline methods on the node classification tasks.

Jiang Zhang, Yuanqing Xia, Ganghui Shen

Autonomous path planning algorithms are significant to planetary exploration rovers, since relying on commands from Earth will heavily reduce their efficiency of executing exploration missions. This paper proposes a novel learning-based algorithm to deal with global path planning problem for planetary exploration rovers. Specifically, a novel deep convolutional neural network with double branches (DB-CNN) is designed and trained, which can plan path directly from orbital images of planetary surfaces without implementing environment mapping. Moreover, the planning procedure requires no prior knowledge about planetary surface terrains. Finally, experimental results demonstrate that DB-CNN achieves better performance on global path planning and faster convergence during training compared with the existing Value Iteration Network (VIN).

Jiang Zhang, Yuanqing Xia, Ganghui Shen

In this paper, emerging deep learning techniques are leveraged to deal with Mars visual navigation problem. Specifically, to achieve precise landing and autonomous navigation, a novel deep neural network architecture with double branches and non-recurrent structure is designed, which can represent both global and local deep features of Martian environment images effectively. By employing this architecture, Mars rover can determine the optimal navigation policy to the target point directly from original Martian environment images. Moreover, compared with the existing state-of-the-art algorithm, the training time is reduced by 45.8%. Finally, experiment results demonstrate that the proposed deep neural network architecture achieves better performance and faster convergence than the existing ones and generalizes well to unknown environment.