Tạp chí Khoa học Công nghệ Hàng Không

Training UGV For Optimal Path Planning Using Reinforcement Learning

Phuong Lan Le — 2026-03-31

In the current era of artificial intelligence technology, unmanned ground vehicles (UGV) are increasingly being widely used in various fields due to the application of advanced technologies such as computer vision and reinforcement learning (RL). These technologies contribute to enhancing the level of automation, environmental awareness, and real-time flexible decision-making capabilities of UGVs. In this paper, we will apply RL with a decaying exploration rate strategy to train UGVs for path planning, obstacle avoidance, and optimal route discovery. Specifically, in the early stages of training, the exploration rate is set to a maximum value so that the agent can explore and collect more information of the state space; as the training time progresses, the exploration rate is gradually reduced, corresponding to a greater focus on the exploitation to find the optimal. Simulation results show that our proposal achieves faster convergence than RL in benchmark, demonstrating the effectiveness of this algorithm for real-world UGV applications.

A Simulation Of Piston Engines Aircraft Based On Wiebe And Woschni Models

Nguyen Quang Vinh — 2026-03-31

This paper presents a combustion simulation for an aircraft piston engine. The aim of this research is to develop a combustion model using accessible and feasible computational tools, ensuring both high accuracy and practicality as a foundation for more advanced studies. The developed model is a zero-dimensional (0-D) and mean-value engine model (MVEM) for a single cylinder, fundamentally based on the first law of thermodynamics. It is meticulously programmed using Matlab, allowing for a detailed description of the intricate relationships among various internal engine characteristics, including cylinder performance parameters, heat release, heat loss, in-cylinder pressure, and an initial estimation of exhaust gas emissions were conducted for the engine operation. Specifically, the heat release process is modeled using the well-established Wiebe function, while heat loss is calculated using the Woschni model, which accounts for the instantaneous heat transfer coefficient. The Runge-Kutta algorithm is employed to solve the differential equations governing the engine's thermodynamic cycles. The research seeks to overcome the inherent limitations of traditional, costly, and time-consuming trial-and-error experimental approaches by leveraging advancements in computational speed and simulation capabilities.

Infrastructure For Safe Distance Management On Expressways: Lessons From France For Vietnam

Dinh Cuong Tran — 2026-03-31

Maintaining a safe distance is a key factor in preventing accidents on expressways. In practice, drivers estimate this distance based on experience, assistance from in-vehicle devices, or support from expressway infrastructure. However, the technical infrastructure on Vietnam’s expressways currently remains limited and lacks continuity in supporting safe distance determination. This study evaluates the current state of technical infrastructure supporting safe distance identification on Vietnamese expressways and compares it with the well-developed system in France. The research collects and analyzes domestic and international regulations, technical requirements, and practical implementations. Results show that infrastructures such as lane markings and signs in Vietnam are installed sporadically, without continuous coverage along the expressway, and are mostly absent in tunnels. In contrast, France systematically integrates safe distance support throughout the entire route, using elements like lane markings and blue lights or chevrons, including inside tunnels. Based on these comparisons, the study proposes improvements for Vietnam by integrating safe distance support into existing infrastructures, such as emergency lane markings, and adding visual signals in tunnels. These improvements should be standardized in regulations and circulars and incorporated into driver training programs to enhance implementation effectiveness and reduce accidents related to safe distance issues.

Smart, Pleasurable, And Influential: Exploring Determinants Of Gen Z’s Willingness To Use Airport Service Robots

Nguyen Duc Nhan Le — 2026-03-31

The rapid integration of service robots in transportation hubs such as airports has transformed how passengers interact with service technologies. As early adopters, Generation Z plays a crucial role in shaping the future of robot-assisted services. This study explores the factors influencing Gen Z passengers’ willingness to use airport service robots through the lens of the Cognitive-Affective-Normative framework. Specifically, the study examines the roles of perceived smartness (cognitive), hedonic value (affective), and social influence (normative) in shaping users’ willingness to use airport service robots . Using a hybrid approach combining Partial Least Squares Structural Equation Modeling and Necessary Condition Analysis, the findings confirm the significance of all three dimensions. Importantly, perceived smartness of service robots and hedonic value emerge as both sufficient and necessary conditions. The study extends the Cognitive-Affective-Normative framework to the airport context and offers practical implications for enhancing service robot design and engagement strategies tailored to Gen Z users

Linking E-Leadership To Digital Adoption In Smes: The Role Of Digital Orientation And Fear Of Failure

Nguyen Thi Vinh Tran — 2026-03-31

In the context of increasing digital transformation, this study investigates the influence of e-leadership on digital technology adoption by examining the mediating role of digital orientation and the moderating effect of fear of failure. Drawing on the Technology–Organization–Environment (TOE) framework and Diffusion of Innovation (DOI) theory, a research model was developed and tested using data collected from 284 employees working in Vietnamese small and medium-sized enterprises (SMEs). Partial Least Squares Structural Equation Modeling (PLS-SEM) was employed to assess the hypothesized relationships. The results indicate that e-leadership positively influences digital technology adoption, both directly and indirectly through digital orientation. Moreover, fear of failure was found to negatively moderate the relationship between e-leadership and technology adoption, but not the relationship between digital orientation and technology adoption. These findings highlight the critical role of digital leadership and individual digital commitment in facilitating adoption, while also emphasizing the need to address psychological barriers. The study offers theoretical contributions by integrating the TOE and DOI frameworks and provides practical insights for organizations navigating digital transformation.

The Impact Of Trust In AI On Inspiration And Intention To Use AI In Teaching Among University Lecturers

Nguyen Anh Loi — 2026-03-31

This study investigates the relationship between trust in AI, inspiration, and faculty intention to use AI in teaching, integrating the technology acceptance model (TAM) and cognitive emotion theory (CET). Using partial least squares structural equation modeling (PLS-SEM), data from 332 university lecturers in Ho Chi Minh City were analyzed. The results reveal that trust in AI outcomes (β = 0.441) and inspiration (β = 0.412) significantly and positively influence intention to use AI in teaching. Notably, inspiration mediates the relationship between trust and intention (indirect effect β = 0.213), highlighting its critical role in translating trust into actionable intentions. The proposed model explains 59.5% of the variance in AI usage intention, confirming its robustness. Additionally, trust in AI outcomes strongly predicts inspiration (β = 0.517), emphasizing the importance of fostering both trust and emotional engagement to enhance AI adoption in higher education. Based on these findings, the study suggests practical strategies, including developing an “AI Trust Ecosystem,” launching an “AI Inspiration Movement,” and implementing an “AI-Integration Roadmap”. These strategies aim to build trust, inspire faculty, and ensure effective AI integration in teaching practices. The study contributes to expanding TAM by incorporating emotional factors from CET, offering a novel perspective on technology acceptance in education.