In the domain of intelligent driving, enhancing the precision of integrated positioning systems remains a critical challenge. The Kalman filter (KF) is a widely adopted approach to address this issue. However, the traditional Kalman filter using linear model and fixed noise model will affect the estimation accuracy of the system. To address the shortcomings of the traditional Kalman filter in integrated positioning systems, this paper proposes an adaptive extended Kalman filter (AEKF). The AEKF uses the covariance matching principle (CMP) and singular spectrum analysis (SSA) to enhance the accuracy and reliability of positioning systems. It integrates laser inertial odometer (LIO) and real-time kinematic (RTK) technologies. The AEKF based on CMP and SSA is called CMP-SSA-AEKF in this paper. The CMP-SSA-AEKF can adaptively update the process noise covariance matrix and the measurement noise covariance matrix in parallel. It overcomes linearization errors, enhances environmental adaptability, and does not incur significant computational costs. Through comparative analysis, this study tests the CMP-SSA-AEKF, as well as the Extended Kalman filter (EKF) and the Unscented Kalman filter (UKF), using multiple experimental metrics. The results show that the CMP-SSA-AEKF is superior to the conventional EKF and UKF in positioning accuracy and stability.

To address the limitations in feature matching accuracy and system robustness in complex environments of Oriented FAST and Rotated BRIEF SLAM2(ORB SLAM2) algorithm, this paper introduces a lightweight neural network MLP and Transformer algorithm combined with ORB SLAM2. The approach begins by using a lightweight neural network to optimize the original feature points and descriptors, generating high-quality feature descriptors. Then, it is integrated into the ORB SLAM2 algorithm and tested for performance under conditions of lighting and perspective changes. Experimental evidence confirms that the proposed enhanced ORB SLAM2 significantly improves feature matching accuracy and the system's robustness to illumination and perspective changes, and outperforms several learning-based algorithms under similar conditions. Furthermore, In terms of positioning accuracy and trajectory experiments, the proposed approach achieves significantly better performance compared to the ORB SLAM2 algorithm, which relies on conventional visual methods.

A coordinated control method integrating emergency brake and direct yaw moment control (DYC) for distributed vehicles is established. The model predictive control (MPC) framework incorporates motor characteristics as constraint conditions, with the objective cost function solved using quadratic programming. The weighting of the emergency brake and DYC coordinated control is dynamically adjusted to accommodate various driving conditions. This strategy enables vehicles to achieve maximum braking torque while ensuring lateral stability and effective anti-lock braking. Simulation results demonstrate that the MPC-based coordinated control significantly improve lateral stability and brake performance. Vehicle brake in approximately 2.5 seconds with yaw rate error less than 0.05 rad/s during emergency braking while cornering.

For the four-wheel independent drive electric vehicle differential steering trajectory tracking problem, a model predictive control (MPC) based trajectory tracking control method is designed. Firstly, a two degree of freedom differential steering vehicle kinematic model is established, and the wheel speeds corresponding to the target trajectory are calculated based on the vehicle kinematic model. Then, the difference between the actual inner and outer wheel speeds and the reference wheel speed is taken as the control error. Through the upper-level MPC (Model Predictive Control) controller, wheel speed tracking control is performed, and the drive torque is outputted by the lower-level PI (Proportional-Integral) wheel speed controller. By limiting the speed of the wheels whose slip ratio exceeds the threshold, the wheel speeds in the MPC are dynamically constrained to improve trajectory tracking accuracy. Finally, the algorithm is validated through a joint simulation platform of Carsim and Simulink. Simulation results show that the designed trajectory tracking controller can effectively control the vehicle to complete medium-speed (40 km/h) lane-changing trajectory tracking and low-speed (10 km/h) small-radius (10m) trajectory tracking, with a maximum lateral error of 0.17m.

With the widespread use of face masks due to the COVID-19 pandemic, accurate masked face recognition has become more crucial than ever. While several studies have investigated masked face recognition using convolutional neural networks (CNNs), there is a paucity of research exploring the use of plain Vision Transformers (ViTs) for this task. Unlike ViT models used in image classification, object detection, and semantic segmentation, the model trained by modern face recognition losses struggles to converge when trained from scratch. To this end, this paper initializes the model parameters via a proxy task of patch reconstruction and observes that the ViT backbone exhibits improved training stability with satisfactory performance for face recognition. Beyond the training stability, two strategies based on prompts are proposed to integrate holistic and masked face recognition in a single framework, namely FaceT. Along with popular holistic face recognition benchmarks, several open-sourced masked face recognition benchmarks are collected for evaluation. Our extensive experiments demonstrate that the proposed FaceT performs on par or better than state-of-the-art CNNs on both holistic and masked face recognition benchmarks. Codes will be made available at https://github.com/zyainfal/Joint-Holistic-and-Masked-Face-Recognition.

This paper presents a robust H∞path following control strategy for autonomous ground vehicles with delays and data dropouts. The state measurements and signal transmissions usually suffer from inevitable delays and data packet dropouts, which may degrade the control performance or even deteriorate the system stability. A robust H∞state-feedback controller is proposed to achieve the path following and vehicle lateral control simultaneously. A generalized delay representation is formulated to include the delays and data dropouts in the measurement and transmission. The uncertainties of the tire cornering stiffnesses and the external disturbances are also considered to enhance the robustness of the proposed controller. Two simulation cases are presented with a high-fidelity and full-car model based on the CarSim-Simulink joint platform, and the results verify the effectiveness and robustness of the proposed control approach.

As one of the most widely implemented standards for wireless networks, IEEE 802.15.4 defines physical and MAC specifications for low data rate wireless personal area networks (WPANs). To accurately analyze the performance of slotted CSMA/CA (SCSMA) algorithms for saturated uplink traffic with acknowledgement (ACK) and non-ACK modes, we adopt an embedded Markov chain based model in the MAC layer of the standard. From the analytic model, we optimize network throughput considering the number of 802.15.4 devices and the data payload by nonlinear programming (NLP). Moreover, according to analytical results of optimization, we propose an adaptive backoff mechanism for maximizing throughput by an approximate and simple Markov model. Furthermore, we present performance evaluation and comparison of IEEE 802.15.4 SCSMA protocol with our approach quantitatively with respect to saturation throughput and probability of successful transmission. Comparing with the SCSMA protocol of IEEE standard through the simulation, our scheme can improve network throughput with non-ACK and ACK modes up to 4.8% and 8.1% on average, respectively. The performance analysis also shows that the network scalability is improved, that is the system can accommodate more contending devices in our proposal.

In this paper, we present a novel 2-way handshake authentication protocol to locally authorize intra-domain roaming users for efficient authentication in mobile IP networks, which is based on authentication, authorization and accounting (AAA) architecture. We develop a detailed procedure to establish local security associations (SAs) for re-authentication using commitment schemes. By considering the traffic and mobility patterns of a mobile user (MU), as well as the message transmission time between the MU and its home AAA server, we provide a performance study for comparing the authentication latency of existing authentication protocol with our approach. The result shows that our protocol outperforms the existing authentication protocol.