Over the past few decades, as vehicles have become increasingly intelligent, the applications of in-vehicle electronic systems have expanded significantly. However, with the growing complexity of vehicle networks, the...
详细信息
ISBN:
(纸本)9781728190549
Over the past few decades, as vehicles have become increasingly intelligent, the applications of in-vehicle electronic systems have expanded significantly. However, with the growing complexity of vehicle networks, there is an ever-increasing concern for their network security. In particular, the controller Area network (CAN) bus has become a critical medium for communication between various Electronic control Units (ECUs) within a vehicle. Since the design of the CAN bus lacks sufficient security measures, it is vulnerable to various network intrusions. To address this security challenge, researchers have been searching for ways to enhance the network security of the CAN bus to ensure that vehicle systems are not compromised by unauthorized access or network attacks. This paper introduces a robust intrusion detection system (IDS) for the CAN bus in vehicles, employing a novel Multi-Scale Feature Fusion technique. Leveraging the distinct capabilities of Long Short-Term Memory (LSTM), Convolutional Neural networks (CNN), and Transformer neural network architectures, the proposed methodology adeptly captures and prioritizes both shallow and deep features of CAN bus data. Besides, it enhances detection accuracy and robustness against various cyber-attacks. Evaluation on the Car-hacking dataset demonstrates superior performance, achieving a precision, recall, and F1-score of 100%. Verified by an ablation study, this approach promises a substantial advancement in safeguarding in-vehicle networks.
To improve the operational stability of high-speed maglev trains and their ability to respond to disturbance excitations, this paper designs a control algorithm based on fuzzy neural networks and backstepping control ...
详细信息
In this paper, in the context of distributed control of heterogeneous battery energy storage systems in a droop control microgrid, based on the consensus theory of multi-agent systems, this paper proposes a distribute...
详细信息
A robust attitude control scheme based on disturbance observer is designed to meet the attitude control requirements of quadrotor UAV. The H-infinity control problem of a class of non-affine nonlinear systems based on...
详细信息
ISBN:
(纸本)9798350334722
A robust attitude control scheme based on disturbance observer is designed to meet the attitude control requirements of quadrotor UAV. The H-infinity control problem of a class of non-affine nonlinear systems based on neural network is studied. A controller based on neural network is designed, which can not only ensure the stability of the closed-loop system, but also reduce the influence of interference on tracking to a given performance index. By means of implicit function theorem, Taylor formula and mean value theorem, the non-affine nonlinear system is transformed into affine nonlinear system. The designed controller is composed of equivalent controller and H-infinity controller. Finally, the effectiveness of the proposed method is proved by theoretical analysis.
Safety-critical applications rely on controlsystems-managed components, which not only have demanding requirements in terms of accuracy, but also require transparency and interpretability, to ensure trustworthiness. ...
详细信息
The convolutional operations of convolutional neural networks (CNNs) on images are untargeted, and the high model complexity of CNNs makes them less suitable for deployment on low-performance devices. According to the...
详细信息
This paper develops an adaptive traffic control policy inspired by Maximum Pressure (MP) while imposing coordination across intersections. The proposed Coordinated Maximum Pressure-plus-Penalty (CMPP) control policy f...
详细信息
We present ReLU-QP, a GPU-accelerated solver for quadratic programs (QPs) that is capable of solving high-dimensional control problems at real-time rates. ReLU-QP is derived by exactly reformulating the Alternating Di...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
We present ReLU-QP, a GPU-accelerated solver for quadratic programs (QPs) that is capable of solving high-dimensional control problems at real-time rates. ReLU-QP is derived by exactly reformulating the Alternating Direction Method of Multipliers (ADMM) algorithm for solving QPs as a deep, weight-tied neural network with rectified linear unit (ReLU) activations. This reformulation enables the deployment of ReLU-QP on GPUs using standard machine-learning toolboxes. We evaluate the performance of ReLU-QP across three model-predictive control (MPC) benchmarks: stabilizing random linear dynamical systems with control limits, balancing an Atlas humanoid robot on a single foot, and performing a whole-body pick-up motion on a quadruped equipped with a six-degree-of-freedom arm. These benchmarks indicate that ReLU-QP is competitive with state-of-the-art CPU-based solvers for small-to-medium-scale problems and offers order-of-magnitude speed improvements for larger-scale problems.
A false data injection attack in a wireless sensor network for cyber physical systems is designed. System state estimation is analyzed by remote distributed consensus estimators, and the Kullback-Leibler divergence is...
详细信息
ISBN:
(纸本)9798350334722
A false data injection attack in a wireless sensor network for cyber physical systems is designed. System state estimation is analyzed by remote distributed consensus estimators, and the Kullback-Leibler divergence is utilized as an indicator of the attack's stealthiness. The attack studied in this paper is injected into the wireless network channel between sensors and is Gaussian distributed with an arbitrary mean. Based on the relationship between the system performance under attack and stealthiness, a constrained optimization problem is given, and the optimal attack strategy can be calculated by solving the problem through the Lagrange multiplier method. Then based on theoretical research, the algorithm for generating the attack sequence is summarized. Finally, the theoretical analysis is justified through a numerical simulation example.
This paper presents a coverage control algorithm specialized to image sampling for 3D model reconstruction of environment using a drone network. It is widely known that the sampling the environment from rich viewing a...
详细信息
ISBN:
(纸本)9798331544461;9784907764838
This paper presents a coverage control algorithm specialized to image sampling for 3D model reconstruction of environment using a drone network. It is widely known that the sampling the environment from rich viewing angles enhances the 3D model quality. To this end, the authors presented so-called angle-aware coverage control based on the concept of constraint-based control, which enables drones to determine its translational motion and camera rotation so that a performance constraint is enforced. In this paper, we combine this control methodology with the battery charging constraint in order to ensure mission persistency. Now, dynamically assigning charging stations to drones is expected to enhance the coverage performance. We thus design a distributed assignment algorithm of the stations based on so-called alternating direction method of multipliers (ADMM). The algorithm is then integrated with the above constraint-based controller, and the integrated system is demonstrated through simulation in Robot Operating System 2.
暂无评论