The cooperative control problem for cyber-physical systems under actuator faults and denial-of-service attacks is investigated, where each subsystem can be modeled by an agent and denial-of-service attacks are viewed as attacks against the inter-agent communication. Specifically, a scenario is considered in which the communication topology loses connectivity following a denial-of-service attack. To address the above problem, a fully distributed secure control strategy is proposed. This strategy combines a distributed observer with an observer-based fault-tolerant consensus control method. Therein, the assumptions that the leader’s communication links are unbreakable and the switched topology contains a spanning tree are further relaxed based on the idea of a jointly connected topology. In addition, this paper also has the following features: Firstly, the proposed scheme eliminates the need for all agents to have prior knowledge of the leader’s dynamics, making the scenario considered in this work more general and applicable. Secondly, the control method presented in this paper does not rely on any global topology information, allowing it to be implemented in a completely distributed manner. Building on the proposed scheme, even under denial-of-service attacks and actuator faults, the consensus problem for cyber-physical systems can be realized. Finally, simulations are provided to demonstrate the effectiveness of the proposed method.

This paper mainly focuses on secure fault-tolerant control for nonlinear cyber-physical systems under the influence of multiple threats, i.e., sensor and actuator saturations, actuator fault, and intermittent denial-of-service attacks. A novel secure fault-tolerant control method is proposed within the Takagi-Sugeno fuzzy modeling framework, considering both saturation constraints and intermittent denial-of-service attacks, to ensure the secure performance of cyber-physical systems under multiple threats. By leveraging the advantages of the proposed method, the influence of outdated information caused by denial-of-service attacks is mitigated, and more precise state/fault estimations are obtained. Furthermore, the method guarantees the stability of both the estimation error system and the closed-loop system, even in the presence of intermittent denial-of-service attacks and saturation constraints. Finally, the effectiveness of this method is validated through experiment.

This paper investigates the problem of secure control for input saturated nonlinear cyber-physical systems (CPSs) subject to faults and multi-channel non-periodic denial-of-service (DoS) attacks. First, the model is reconstructed where the nonlinear characteristics can be described by using the Takagi-Sugeno (T-S) fuzzy modeling technique. Then, with the help of the sampling mechanism and the anti-windup compensator, a sampled data-based anti-windup fault-tolerant control scheme with membership function mismatch is proposed. This scheme effectively mitigates the impact of faults while alleviating performance degradation caused by input saturation. Furthermore, to address the challenges posed by multi-channel non-periodic DoS attacks, a resilient observer-based anti-windup secure fault-tolerant control strategy is further proposed to guarantee system stability. Finally, the simulation results are also given to verify the validity of the proposed method.

This article mainly focuses on the problem of observer-based adaptive event-triggered security fault-tolerant control (FTC) for attacked cyber-physical systems (CPSs). First, for the nonlinear characteristics in CPSs, the model is reconstructed based on the Takagi-Sugeno (T-S) fuzzy modeling technique. Then, a T-S fuzzy resilient observer is proposed to estimate the state as well as the actuator fault information. The proposed T-S fuzzy resilient observer proactively detects sensor transmission channels affected by dynamically changing denial-of-service (DoS) attacks, and proactively isolates contaminated data so as to reduce the impact of DoS attacks on the estimation effect. Based on the above content, an observer-based adaptive event-triggered security FTC scheme is proposed, which can ensure the stability of the CPSs and save the limited network resources between the controller and the actuator. Finally, simulation results are given to verify the effectiveness of the proposed scheme.

Ideal part editing should guarantee the diversity of edited parts, the fidelity to the remaining parts, and the quality of the results. However, previous methods do not disentangle each part completely, which means the edited parts will affect the others, resulting in poor diversity and fidelity. In addition, some methods lack constraints between parts, which need manual selections of edited results to ensure quality. Therefore, we propose a four-stage process for point cloud part editing: Segmentation, Generation, Assembly, and Selection. Based on this process, we introduce SGAS, a model for part editing that employs two strategies: feature disentanglement and constraint. By independently fitting part-level feature distributions, we realize the feature disentanglement. By explicitly modeling the transformation from object-level distribution to part-level distributions, we realize the feature constraint. Considerable experiments on different datasets demonstrate the efficiency and effectiveness of SGAS on point cloud part editing. In addition, SGAS can be pruned to realize unsupervised part-aware point cloud generation and achieves state-of-the-art results.

Cross-modal knowledge transfer enhances point cloud representation learning in LiDAR semantic segmentation. Despite its potential, the weak teacher challenge arises due to repetitive and non-diverse car camera images and sparse, inaccurate ground truth labels. To address this, we propose the Efficient Image-to-LiDAR Knowledge Transfer (ELiTe) paradigm. ELiTe introduces Patch-to-Point Multi-Stage Knowledge Distillation, transferring comprehensive knowledge from the Vision Foundation Model (VFM), extensively trained on diverse open-world images. This enables effective knowledge transfer to a lightweight student model across modalities. ELiTe employs Parameter-Efficient Fine-Tuning to strengthen the VFM teacher and expedite large-scale model training with minimal costs. Additionally, we introduce the Segment Anything Model based Pseudo-Label Generation approach to enhance low-quality image labels, facilitating robust semantic representations. Efficient knowledge transfer in ELiTe yields state-of-the-art results on the SemanticKITTI benchmark, outperforming real-time inference models. Our approach achieves this with significantly fewer parameters, confirming its effectiveness and efficiency.

In point cloud generation and completion, previous methods for transforming latent features to point clouds are generally based on fully connected layers (FC-based) or folding operations (Folding-based). However, point clouds generated by FC-based methods are usually troubled by outliers and rough surfaces. For folding-based methods, their data flow is large, convergence speed is slow, and they are also hard to handle the generation of non-smooth surfaces. In this work, we propose AXform, an attention-based method to transform latent features to point clouds. AXform first generates points in an interim space, using a fully connected layer. These interim points are then aggregated to generate the target point cloud. AXform takes both parameter sharing and data flow into account, which makes it has fewer outliers, fewer network parameters, and a faster convergence speed. The points generated by AXform do not have the strong 2-manifold constraint, which improves the generation of non-smooth surfaces. When AXform is expanded to multiple branches for local generations, the centripetal constraint makes it has properties of self-clustering and space consistency, which further enables unsupervised semantic segmentation. We also adopt this scheme and design AXformNet for point cloud completion. Considerable experiments on different datasets show that our methods achieve state-of-the-art results.

Point cloud completion aims to recover a complete shape of a 3D object from its partial observation. Existing methods usually predict complete shapes from global representations, consequently, local geometric details may be ignored. Furthermore, they tend to overlook relations among different local regions, which are valuable during shape inference. To solve these problems, we propose a novel point cloud completion network based on multi-scale edge convolution and attention mechanism, named MEAPCN. We represent a point cloud as a set of embedded points, each of which contains geometric information of local patches around it. Firstly, we devise an encoder to extract multi-scale local features of the input point cloud and produce partial embedded points. Then, we generate coarse complete embedded points to represent the overall shape. In order to enrich features of complete embedded points, attention mechanism is utilized to selectively aggregate local informative features of partial ones. Lastly, we recover a fine-grained point cloud with highly detailed geometries using folding-based strategy. To better reflect real-world occlusion scenarios, we contribute a more challenging dataset, which consists of view-occluded partial point clouds. Experimental results on various benchmarks demonstrate that our method achieves a superior completion performance with much smaller model size and much lower computation cost.

Generative Adversarial Networks (GAN) are good at generating variant samples of complex data distributions. Generating a sample with certain properties is one of the major tasks in the real-world application of GANs. In this paper, we propose a novel generative adversarial network to generate 3D point clouds from random latent codes, named Controllable Point Cloud Generative Adversarial Network(CPCGAN). A two-stage GAN framework is utilized in CPCGAN and a sparse point cloud containing major structural information is extracted as the middle-level information between the two stages. With their help, CPCGAN has the ability to control the generated structure and generate 3D point clouds with semantic labels for points. Experimental results demonstrate that the proposed CPCGAN outperforms state-of-the-art point cloud GANs.