In the field of pedestrian re-identification (ReID), the challenge of matching occluded pedestrian images with holistic images across different camera views is significant. Traditional approaches have predominantly addressed non-pedestrian occlusions, neglecting other prevalent forms such as motion blur resulting from rapid pedestrian movement or camera focus discrepancies. This study introduces the MotionBlur module, a novel data augmentation strategy designed to enhance model performance under these specific conditions. Appropriate regions are selected on the original image for the application of convolutional blurring operations, which are characterized by predetermined lengths and frequencies of displacement. This method effectively simulates the common occurrence of motion blur observed in real-world scenarios. Moreover, the incorporation of multiple directional blurring accounts for a variety of potential situations within the dataset, thereby increasing the robustness of the data augmentation. Experimental evaluations conducted on datasets containing both occluded and holistic pedestrian images have demonstrated that models augmented with the MotionBlur module surpass existing methods in overall performance.

Through the deployment of bibliometric techniques and network visualizations, this analysis synthesizes the evolution and trajectories of autonomous driving research from 2002 to May 2024, as captured in the Scopus database encompassing 342 scholarly documents. This study was conducted to delineate the developmental contours, thematic emphases, and the expansive growth trajectory within this field, particularly noting a surge in scholarly outputs since 2017. Such growth has been primarily facilitated by breakthroughs in artificial intelligence and sensor technologies, along with burgeoning interdisciplinary collaborations and escalating academic and industrial investments. A meticulous examination of publication trends, document types, subject areas, and geographic distributions elucidates the multidisciplinary and international nature of this burgeoning field. Key thematic clusters identified—comprising foundational technologies, environmental sustainability, safety measures, regulatory frameworks, user experience, connectivity, and technological innovations—underscore the prevailing research directions and emerging focal areas poised to shape future autonomous mobility solutions. Notably, increased emphasis on environmental sustainability and regulatory frameworks has been observed, highlighting their critical roles in advancing and integrating autonomous driving systems. This study provides pivotal insights for researchers, policymakers, and industry stakeholders, fostering a nuanced understanding of the field’s dynamics and facilitating strategic alignments and innovations in autonomous mobility. The emergent research domains and collaborative networks revealed herein not only map the current landscape but also guide future scholarly endeavors in autonomous driving systems globally.

The towing limits for self-propelled rail track maintenance equipment (SP-TME) are influenced by a multitude of factors, including the type and weight of the equipment, speed, braking capabilities, track and weather conditions, traction, engine power, driveline performance, coupler/towing link integrity, and safety regulations. This study investigates these variables to determine their impact on the towing limits of SP-TME. Unlike traditional rail vehicles, SP-TME possesses unique operational constraints and specifications, necessitating careful consideration of its independent mobility. An extensive analysis was conducted on the towing usage and overuse of SP-TME during travel mode, examining various scenarios that incorporate different combinations of trailing load, rail track grade, rail curvature, and weather conditions. These scenarios, ranging from normal to worst-case, aim to simulate demanding operational environments. The parameters evaluated include structural strength, traction, engine and driveline performance, wheel rolling and skidding, braking capabilities, trailing load, speed, and track and weather conditions. Results indicate that under normal and moderate conditions, the equipment can tow significantly higher loads than the defined base load. However, in special situations, such as negotiating tighter curves and steeper grades in adverse weather conditions, wheel skidding and locking emerge as limiting factors. Findings related to service and parking brake performance during steep grade descents, particularly when the trailer lacks independent braking capabilities, are also presented. Recommendations and cautions are provided to ensure safe and efficient operation of SP-TME under various conditions.

A comprehensive analysis of vehicle collision dynamics is presented using a two-mass model that simulates the impact of a vehicle against a rigid barrier. The model incorporates dual springs and dampers to examine the influence of spring stiffness and damping on a mass attached to the vehicle. The equations of motion are solved utilizing state variables, while energy principles are employed to establish correlations between vehicle deformation, impact force, and acceleration. Validation is conducted through comparison with crash test data from a 2023 Honda Accord LX 4-Door Sedan. Average deformation values are used to calculate acceleration, followed by a Monte Carlo simulation to analyze acceleration data recorded by the engine sensor, enabling the determination of vehicle speed through integration. Parametric regression is applied to optimize model parameters, resulting in a high degree of concordance between experimental and theoretical values. The model's accuracy is further verified through the analysis of velocity and deceleration profiles and the integration of the deceleration curve. The findings underscore the model's capability to replicate real-world crash dynamics, highlighting its potential to enhance vehicle safety system design. The innovation of this research lies in its simplified yet effective approach to modeling collision dynamics, offering significant insights into the relationship between vehicle deformation and occupant forces. This work advances the understanding of vehicle collision mechanics and provides a robust tool for the development of advanced safety features. The integration of theoretical and empirical data reinforces the model's reliability, contributing substantively to the field of automotive safety engineering.

Maglev transportation, as an innovative mode of rail transit, is regarded as an ideal future transportation system due to its wide speed range, low noise, and strong climbing ability. However, the maglev control system faces challenges such as significant nonlinearity, open-loop instability, and multi-state coupling, leading to issues like insufficient tuning and susceptibility to environmental influences. This paper addresses these problems by investigating the self-tuning parameters of a maglev control system using Q-learning to achieve optimal parameter tuning and enhanced dynamic system performance. The study focuses on a basic levitation unit modeled after the simplified control system of an electromagnetic suspension (EMS) train. A Q-learning reinforcement learning environment and Q-learning agent were established for the levitation system, with a forward "anti-deadlock" reward function and discretization of the action space designed to facilitate reinforcement learning model training. Finally, a Q-learning-based method for self-tuning the parameters of the maglev control system is proposed. Simulation results in the Python environment demonstrate that this method outperforms the Linear Quadratic Regulator (LQR) control method, offering better control effects, improved robustness, and higher tracking accuracy under system parameter perturbations.