Transportation Research Interdisciplinary Perspectives最新文献_第4页

The effect of training on law enforcement response to vehicle cybersecurity events 培训对执法部门应对车辆网络安全事件的影响

IF 3.8

Transportation Research Interdisciplinary Perspectives Pub Date : 2025-09-22 DOI: 10.1016/j.trip.2025.101644

Jaji Pamarthi, William Hanson, Nandni Talreja, Meng Wang, Shannon C. Roberts

{"title":"The effect of training on law enforcement response to vehicle cybersecurity events","authors":"Jaji Pamarthi, William Hanson, Nandni Talreja, Meng Wang, Shannon C. Roberts","doi":"10.1016/j.trip.2025.101644","DOIUrl":"10.1016/j.trip.2025.101644","url":null,"abstract":"<div><div>Emerging technologies have revolutionized driving by providing a safer and more comfortable experience. However, most vehicles – including those used by law enforcement officers – overlook cybersecurity considerations, leaving them susceptible to cyberattacks. At this critical juncture, as technology becomes increasingly integrated into the vehicle fleet, it is important to enhance awareness of cybersecurity risks in vehicles. This mixed methods study investigates the impacts of a training program on law enforcement officers’ behavior using a driving simulator study and interviews. Thirteen law enforcement officers completed the study, revealing varied reactions to three vehicle cyberattacks. There is a difference between those who received Advanced Training and those who receive Basic Training in terms of their conceptual understanding, but not necessarily in how they respond to cybersecurity events. The study highlighted a lack of comprehension regarding vehicle cybersecurity among participants, indicating a need for enhanced training and awareness initiatives to fortify law enforcement’s officers’ cybersecurity response capabilities.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"34 ","pages":"Article 101644"},"PeriodicalIF":3.8,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145108009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Determinants of intercity mode choice preferences and travel behavior in a border tourism city 边境旅游城市城际模式选择偏好与出行行为的决定因素

IF 3.8

Transportation Research Interdisciplinary Perspectives Pub Date : 2025-09-22 DOI: 10.1016/j.trip.2025.101638

Tosporn Arreeras , Sayam Sunmud , Kittichai Thanasupsin , Suchada Phonsitthangkun

{"title":"Determinants of intercity mode choice preferences and travel behavior in a border tourism city","authors":"Tosporn Arreeras , Sayam Sunmud , Kittichai Thanasupsin , Suchada Phonsitthangkun","doi":"10.1016/j.trip.2025.101638","DOIUrl":"10.1016/j.trip.2025.101638","url":null,"abstract":"<div><div>This study examines the intercity mode choice preferences and travel characteristics of tourists in Chiang Rai, a notable border tourism city in northern Thailand. Despite growing tourism demand, the region faces persistent transport infrastructure challenges, which are underrepresented in the literature that predominantly focuses on metropolitan contexts. This gap limits the understanding of mobility dynamics in secondary cities crucial to regional tourism development. Utilizing a multinomial logit (MNL) model, data from 403 non-residents of Chiang Rai were analyzed to identify the determinants influencing travelers’ transportation choices among various modes, including air transport, public buses, and private cars. The results indicate that demographic factors such as age, gender, and income, in conjunction with travel-specific variables like trip purpose, travel time, and cost, significantly influence mode choice. The preference for private cars over public transportation underscores the need for enhancing public transport infrastructure to improve the tourist experience and support sustainable tourism development. This study contributes empirical evidence on tourist travel behavior in a border city, underscoring the importance of socioeconomic and trip-related factors in mode choice. The findings support the need for targeted policies and infrastructure upgrades to foster sustainable transport and enhance Chiang Rai’s tourism appeal.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"34 ","pages":"Article 101638"},"PeriodicalIF":3.8,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145108008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Transport infrastructure investments and economic transformation in South Africa: The case of integrated public transport network in the Gauteng Province 南非交通基础设施投资与经济转型：以豪登省综合公共交通网络为例

IF 3.8

Transportation Research Interdisciplinary Perspectives Pub Date : 2025-09-20 DOI: 10.1016/j.trip.2025.101637

Alexis Habiyaremye, Makgapjane Toloki Thobela, Charles Shaaba Saba

{"title":"Transport infrastructure investments and economic transformation in South Africa: The case of integrated public transport network in the Gauteng Province","authors":"Alexis Habiyaremye, Makgapjane Toloki Thobela, Charles Shaaba Saba","doi":"10.1016/j.trip.2025.101637","DOIUrl":"10.1016/j.trip.2025.101637","url":null,"abstract":"<div><div>With the unemployment in South Africa reaching 32.5 %, rising inequality, poverty, and low growth rates, investment in infrastructure projects like the Integrated Public Transport Network (IPTNs) is a strategic tool in the hands of government to transform the economy. This article examines the IPTN infrastructure project in the Gauteng Province to analyse its contribution to local economic transformation and skills development. The research is designed as a deep-dive case study in which pertinent data are collected from multiple stakeholders through semi-structured interviews, and triangulated through available internal and external documents. The research sample comprises IPTN planners, contractor and sub-contractor small-, medium- or micro-enterprises (SMMEs), an executive from a bus manufacturing firm, and representatives from the transformed taxi industry. The main findings from the study reveal that infrastructure investments in IPTNs have been instrumental in fostering job creation, driving skills development, supporting SMME growth, and spurring a surge in local bus manufacturing. The case study for successful vehicle operating companies (VOCs) suggests that further investigation into other manufacturing opportunities and skills development is needed to provide additional evidence of infrastructure investment spillovers.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"34 ","pages":"Article 101637"},"PeriodicalIF":3.8,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145098488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Understanding future adoption of autonomous vehicle services among disabled and non-disabled users 了解未来自动驾驶汽车服务在残疾人和非残疾人用户中的应用

IF 3.8

Transportation Research Interdisciplinary Perspectives Pub Date : 2025-09-19 DOI: 10.1016/j.trip.2025.101602

Shravani Sharma , Roger Woodman , Neel Ocean , Mark T. Elliott

{"title":"Understanding future adoption of autonomous vehicle services among disabled and non-disabled users","authors":"Shravani Sharma , Roger Woodman , Neel Ocean , Mark T. Elliott","doi":"10.1016/j.trip.2025.101602","DOIUrl":"10.1016/j.trip.2025.101602","url":null,"abstract":"<div><div>Autonomous vehicles (AVs) are poised to transform mobility, yet their adoption depends on both subjective and objective factors. While objective factors like cost and accessibility are well studied, subjective factors, such as trust, perceived safety, and wellbeing, become particularly crucial when users may have not yet experienced these new transport modes. Existing research often treats AVs as a singular concept, overlooking the diversity of AV services and their varying appeal across populations. This study bridges this gap by comparing adoption preferences for multiple AV services, including AV Taxis, AV Remote Taxis, AV Micro Cars, AV Private Cars and AV Buses, across disabled and non-disabled populations. Using sentiment analysis and statistical analysis, we examine how wellbeing, assistance availability, design etc. influence transport choices. Findings vary across mental health, physical health, and non-disabled populations for different AV services. These insights provide a framework for policymakers and industry leaders to design equitable and inclusive AV systems globally.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"34 ","pages":"Article 101602"},"PeriodicalIF":3.8,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145098486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Impact of acute glucose episodes on adherence to speed limits in the naturalistic setting for drivers with diabetes: An application of linear quantile mixed models 急性血糖发作对糖尿病司机遵守车速限制的影响：线性分位数混合模型的应用

IF 3.8

Transportation Research Interdisciplinary Perspectives Pub Date : 2025-09-19 DOI: 10.1016/j.trip.2025.101633

Aparna Joshi , Archana Venkatachalapathy , Jennifer Merickel , Jun Ha Chang , Matthew Rizzo , Soumik Sarkar , Anuj Sharma

{"title":"Impact of acute glucose episodes on adherence to speed limits in the naturalistic setting for drivers with diabetes: An application of linear quantile mixed models","authors":"Aparna Joshi , Archana Venkatachalapathy , Jennifer Merickel , Jun Ha Chang , Matthew Rizzo , Soumik Sarkar , Anuj Sharma","doi":"10.1016/j.trip.2025.101633","DOIUrl":"10.1016/j.trip.2025.101633","url":null,"abstract":"<div><div>Diabetes can cause complications from hypoglycemic and hyperglycemic episodes, impairing cognitive and motor skills essential for safe driving. Advances in low-cost sensors and wearable technologies have enabled naturalistic driving studies (NDS) that simulate real-world conditions while monitoring drivers’ blood glucose levels. This paper analyzes data from an NDS conducted in Nebraska, focusing on how drivers with Type 1 Diabetes Mellitus (T1DM) and Type 2 Diabetes Mellitus (T2DM), as well as control participants without diabetes, adhere to speed limits of 50–75 mph on highways. Alongside a conventional Linear Mixed Effects Model (LMM), we introduce a novel Linear Quantile Mixed Effects Model (LQMM) to evaluate six quantiles (τ = 0.10, 0.25, 0.50, 0.75, 0.85, and 0.90) of speed limit adherence during acute glucose episodes, including hyperglycemia and hypoglycemia. Findings show that hypoglycemia generally leads T1DM drivers to drive more cautiously and remain below speed limits. No significant effects of hypoglycemia or hyperglycemia were observed on T2DM drivers’ speed adherence, suggesting glycemic fluctuations may not substantially influence their behavior. Hyperglycemia was linked to increased caution among T1DM drivers, consistent with evidence of heightened physiological awareness in this group. Control drivers exceeded speed limits more often than those with diabetes, especially relative to T2DM drivers. Roadway characteristics (e.g., traffic flow and speed limits) and age also influence speed behavior, highlighting important contextual factors. By utilizing distribution-based methods like LQMMs that account for participant heterogeneity, this paper presents a nuanced view of speed control patterns, yielding new insights into how diabetes affects driving safety.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"34 ","pages":"Article 101633"},"PeriodicalIF":3.8,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145098487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comparing econometric and machine learning models to fare evasion prediction 比较计量经济学和机器学习模型对逃票预测的影响

IF 3.8

Transportation Research Interdisciplinary Perspectives Pub Date : 2025-09-18 DOI: 10.1016/j.trip.2025.101636

Benedetto Barabino, Roberto Ventura

{"title":"Comparing econometric and machine learning models to fare evasion prediction","authors":"Benedetto Barabino, Roberto Ventura","doi":"10.1016/j.trip.2025.101636","DOIUrl":"10.1016/j.trip.2025.101636","url":null,"abstract":"<div><div>Fare evasion poses a significant financial threat to Transit Agencies (TAs) and Public Transport Companies (PTCs) globally, especially within Proof-of-Payment Transit Systems (POP-TSs). Understanding and estimating fare evasion frequency is crucial for developing targeted countermeasures. Traditionally, Econometric Models (EMs) have been employed for this purpose, linking fare evasion frequency to specific predictors to assess their effects and significance. However, Machine Learning Models (MLMs) have recently emerged as promising tools, offering the potential for enhanced accuracy through complex data analysis. Despite their strengths, a comprehensive comparison between EMs and MLMs for predicting fare evasion frequency has been lacking in the literature.</div><div>This study addresses this gap by developing, calibrating, and validating two alternative frequency estimation models—an EM based on a Generalised Linear Regression Model (GLRM) and an MLM based on an Artificial Neural Network Model (ANNM). Using 4,000- real-world records from an Italian mid-sized PTC, the models’ performances are quantitatively assessed through regression plots, error metrics, and fare evasion event ratios. The findings indicate that ANNM slightly outperforms GLRM on the considered dataset, showing a higher correlation coefficient, reduced margin of error, and a fare evasion event ratio closer to one. Moreover, the predictor effects were explored, an area where ANNM’s “black box” nature traditionally limits transparency. An overview of these effects shows that while both models identify similar key factors, each prioritises different aspects of fare evasion influences. These insights would help TAs/PTCs select models based on data, interpretability needs, and fare evasion patterns, supporting more effective, data-driven management strategies.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"34 ","pages":"Article 101636"},"PeriodicalIF":3.8,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145098485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Experimental trust dynamics modelling in supervised autonomous ship navigation in collision avoidance scenarios 有监督自主船舶避碰导航实验信任动力学建模

IF 3.8

Transportation Research Interdisciplinary Perspectives Pub Date : 2025-09-18 DOI: 10.1016/j.trip.2025.101634

Rongxin Song , Eleonora Papadimitriou , Rudy R. Negenborn , Pieter van Gelder

{"title":"Experimental trust dynamics modelling in supervised autonomous ship navigation in collision avoidance scenarios","authors":"Rongxin Song , Eleonora Papadimitriou , Rudy R. Negenborn , Pieter van Gelder","doi":"10.1016/j.trip.2025.101634","DOIUrl":"10.1016/j.trip.2025.101634","url":null,"abstract":"<div><div>Maritime Autonomous Surface Ships (MASS) are advancing the shipping industry, requiring a mixed waterborne transport system (MWTS) where human supervision provides a supporting role for maintaining safety and efficiency, particularly in complex scenarios. This study explores the dynamics of seafarers’ trust in MASS during collision avoidance (CA) scenarios involving a vessel approaching from the starboard side. An empirical study with 26 participants representing diverse maritime experience levels examined how time, demographic factors, and collision avoidance strategies influence trust. Using a linear mixed model (LMM), trust was found to fluctuate across navigation stages: gradual accumulation during the routine navigation stage, sharp dissipation during strategy determination and execution stages, and partial recovery at the final stage. Strategies aligned with maritime regulations and appropriately timed evasive actions fostered higher trust, while overly early or imminent actions reduced trust. Additionally, a factor analysis consolidated the five trust dimensions, including dependability, predictability, anthropomorphism, faith, and safety, into two aspects: System Competence, encompassing the first four dimensions, and Situational Safety, representing safety-related trust. Furthermore, Bayesian Network (BN) is developed to model trust in the autonomous decision-making of MASS, integrating human observers demographics and situational factors. The model captures sequential trust dependencies, revealing the cascading effects of trust across various stages and the role of System Competence in shaping overall trust in the entire decision-making process. These findings provide actionable insights for designing MASS that support trust-building and optimise collision avoidance strategies, contributing to safer and more efficient autonomous maritime operations.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"34 ","pages":"Article 101634"},"PeriodicalIF":3.8,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145098484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The top-down-bottom-up approach: a Mobility Program Indicators Development Framework (MPIDF) 自顶向下、自底向上的方法：流动性计划指标开发框架（MPIDF）

IF 3.8

Transportation Research Interdisciplinary Perspectives Pub Date : 2025-09-17 DOI: 10.1016/j.trip.2025.101635

Matthias Grundei, Carolin Zimmer, Maximilian Pfertner, David Durán-Rodas

{"title":"The top-down-bottom-up approach: a Mobility Program Indicators Development Framework (MPIDF)","authors":"Matthias Grundei, Carolin Zimmer, Maximilian Pfertner, David Durán-Rodas","doi":"10.1016/j.trip.2025.101635","DOIUrl":"10.1016/j.trip.2025.101635","url":null,"abstract":"<div><div>Impact evaluation is frequently used to assess the long-term effects of urban mobility programs and projects. However, there are no specific guidelines for selecting mobility-related evaluation indicators. Typically, indicators for program evaluation are determined top-down. Although this shows a program’s goal achievement, it does not consider the feasibility or contextual meaningfulness of the measurements. Furthermore, the top-down approach might overlook different perspectives. To enhance evaluation performance, this research aims to develop a framework for co-creating indicators for mobility program evaluation: the Mobility Program Indicators Development Framework (MPIDF). The MPIDF combines top-down strategic guidelines with insights from science, industry, and society in an iterative process. This approach enhances the evaluation’s relevance and comprehensiveness, allowing transdisciplinary stakeholders to contribute meaningfully, resulting in more balanced and effective mobility programs. Based on eight top-down-bottom-up steps of the MPIDF, this research applied and evaluated a case study: the MCube Cluster program in Munich, Germany. We established an indicator set to evaluate 11 innovative mobility projects in the MCube program. The implementation demonstrates that the involvement of transdisciplinary stakeholders produces a feasible indicator set. The MPIDF’s flexibility allowed practitioners to customize or redevelop indicators as needed, moving beyond existing standards. Moreover, the MPIDF has the potential to be transferred to indicator development processes of mobility and other programs. Further research should contain a long-term study to investigate the effects of using the MPIDF on the outcomes and the strategic development of mobility programs. Additional studies on the framework’s applicability in programs in other areas would be valuable.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"34 ","pages":"Article 101635"},"PeriodicalIF":3.8,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145098483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Acceptance and usage of demand‑responsive transport among people in poor health: Evidence from Senboku New Town 健康状况不佳的人群对需求响应型交通的接受和使用：来自Senboku新镇的证据

IF 3.8

Transportation Research Interdisciplinary Perspectives Pub Date : 2025-09-16 DOI: 10.1016/j.trip.2025.101632

Haruka Kato

{"title":"Acceptance and usage of demand‑responsive transport among people in poor health: Evidence from Senboku New Town","authors":"Haruka Kato","doi":"10.1016/j.trip.2025.101632","DOIUrl":"10.1016/j.trip.2025.101632","url":null,"abstract":"<div><div>Demand-responsive transport (DRT) is promoted as an inclusive solution to first- and last-mile mobility challenges; however, there is limited information on the opportunities and challenges associated with its adoption by individuals in poor health. This study aimed to identify factors influencing the acceptability and utilization of DRT among these individuals. Senboku New Town (Senboku-NT), a representative Japanese old New-Town, was selected for the investigation. In Senboku-NT, a cross-sector partnership program was implemented to engage local communities in operating the DRT project. The results demonstrated that behavioral intention (BI) was positively influenced by habit (Ha), personal innovativeness (PI), and citizens’ engagement (CE). Additionally, use behavior (UB) was positively affected by Ha and PI. A key finding was the relationship between CE and BI, underscoring the crucial role of community involvement in DRT adoption. The impact of CE on BI was more substantial among individuals in good health compared to those with poor health. However, the findings revealed that BI alone is insufficient to ensure UB, especially for individuals in poor health. Despite a high willingness to use DRT, many individuals in poor health faced barriers, including a lack of nearby mobility spots, unclear location information, and difficulties using smartphone booking systems. The results support the recommendation to increase the density of mobility spots in residential areas to enhance DRT accessibility for vulnerable populations.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"34 ","pages":"Article 101632"},"PeriodicalIF":3.8,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145098167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MST: A Modified Sparse Transformer with depth-aware attention for multi-modal camera–LiDAR fusion in autonomous vehicles MST：一种具有深度感知注意力的改进稀疏变压器，用于自动驾驶汽车中多模态摄像头-激光雷达融合

IF 3.8

Transportation Research Interdisciplinary Perspectives Pub Date : 2025-09-16 DOI: 10.1016/j.trip.2025.101571

Badri Raj Lamichhane , Bibek Paudel , Sushant Paudel , Gun Srijuntongsiri , Teerayut Horanont

{"title":"MST: A Modified Sparse Transformer with depth-aware attention for multi-modal camera–LiDAR fusion in autonomous vehicles","authors":"Badri Raj Lamichhane , Bibek Paudel , Sushant Paudel , Gun Srijuntongsiri , Teerayut Horanont","doi":"10.1016/j.trip.2025.101571","DOIUrl":"10.1016/j.trip.2025.101571","url":null,"abstract":"<div><div>Sensor fusion plays a pivotal role in enhancing the accuracy, safety, and decision-making capabilities of autonomous vehicles by integrating camera and LiDAR data. Cameras provide rich semantic information, while LiDAR offers precise depth estimation; their fusion is crucial for robust perception in complex driving scenarios. Transformer-based models have emerged as effective tools for multimodal fusion by leveraging self-attention to capture intricate relationships between sensor data. However, traditional transformers face computational efficiency challenges with long input sequences and sparse data. To address these limitations, we propose the Modified Sparse Transformer (MST) for camera–LiDAR fusion. The MST reduces attention matrix complexity, enabling faster processing while maintaining high performance with fewer parameters. Key innovations include depth-aware attention mechanisms, cross-modal feature alignment, and dynamic instance interaction modules. These collectively enhance object detection accuracy in challenging conditions such as low visibility and dense traffic. Experiments on benchmark datasets demonstrate significant improvements in both accuracy and efficiency compared to existing methods.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"34 ","pages":"Article 101571"},"PeriodicalIF":3.8,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145098166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0