Quay cranes (QCs) play a vital role in ship-to-shore operations, enabling the seamless transfer of cargo between sea and land. However, increasing trade volumes require faster and more cost-effective container handling, exerting significant pressure on QCs and leading to greater wear on critical components such as wires, hoists, and rope clamps. While operations research has explored maintenance scheduling to improve terminal performance, comparatively little work has examined how machine learning can exploit the growing volume of QC monitoring and operational data to predict breakdowns before they occur. This study contributes to this area by integrating terminal operations data, QC monitoring logs, and meteorological observations into a unified analytical framework. We employ explainable artificial intelligence (XAI), using both global and local SHapley Additive exPlanations (SHAP) to identify the operational and environmental factors most strongly associated with QC failures and to illustrate concrete, instance-level examples of how specific conditions contribute towards breakdowns. In parallel, we develop a robust machine learning pipeline built around nested cross-validation to assess the predictive capability of multiple classifiers for forecasting QC breakdowns. Our XAI analysis reveals that breakdown risk is closely linked to QC working time, the distribution of moves across simultaneously operating QCs, hoist overload and trolley alignment warnings, and adverse weather conditions. Among the evaluated models, LightGBM achieved the highest predictive accuracy, reaching up to 83% in identifying breakdown-prone scenarios. These findings demonstrate the feasibility and value of data-driven predictive maintenance for QCs, providing insights that support safer, more reliable, and more efficient terminal operations. 

Det svenska vägnätet utgör en riskfylld arbetsmiljö där olyckor vid vägarbeten ofta får allvarliga konsekvenser för såväl vägarbetare som trafikanter. Projektets övergripande mål är att öka säkerheten vid vägarbeten. Fokus ligger på förbättrad och tydligare vägledning samt ökad efterlevnad av hastighetsbegränsningar. För att uppnå detta krävs fördjupad kunskap om hur trafikanter uppfattar trafikmiljöer och hur beteenden kan påverkas genom användning av dynamiskt ljus. Syftet med projektet är att undersöka hur dynamiska ljuslösningar, såsom LED-slingor, projicerade symboler och ljusmönster, kan bidra till säker trafikledning vid såväl fasta som rörliga vägarbeten. Resultaten indikerar att vissa typer av dynamiskt ljus, särskilt i bärnstensfärg och i form av projicerade ytor, kan förbättra trafikanters följsamhet till vägledning och bidra till sänkta hastigheter. Dessa lösningar upplevdes som mer intuitiva, mindre stressande och tydligare jämfört med traditionell statisk skyltning Sammanfattningsvis visar studien att dynamiskt ljus har potential att öka säkerheten vid vägarbeten samt utgör ett värdefullt underlag för fortsatt teknikutveckling och vidare arbete med förbättrad vägledning.

The Swedish road network constitutes a high-risk work environment, where accidents at roadworks often result in serious consequences for both road workers and road users. The overall objective of this project is to enhance safety at roadworks, with a particular focus on improving the clarity of guidance and increasing compliance with speed limits. Achieving this requires a deeper understanding of how road users perceive traffic environments and how their behaviour can be influenced through the application of dynamically guiding light. The project specifically investigates the potential of dynamic lighting solutions—such as LED systems, projected symbols, and light patterns—to support safe traffic management at both fixed and mobile roadwork sites. The findings indicate that certain dynamic lighting applications, particularly amber lighting and projected surfaces, can improve compliance with guidance and contribute to reduced speeds. These solutions are also perceived as more intuitive, less stressful, and clearer compared with traditional static signage. In conclusion, the study demonstrates that dynamically guiding light has significant potential to enhance safety at road works and provides a valuable foundation for further technological development and continued efforts to improve traffic guidance.

Många förare har ett avsökningsbeteende som systematiskt missar vissa potentiella konflikter, vilket indikerar att deras mentala modeller är felaktiga. Exempelvis förekommer att förare inte tittar efter cyklister som kommer bakifrån innan de svänger höger. Vi undersöker därför hur avsökningsbeteende och anpassning till situationen varierar med omgivande trafik, körriktning, trafikregler och icke-körrelaterade uppgifter, för att förbättra förståelsen av varför förare gör systematiska fel då de söker av omgivningen.

En körsimulatorstudie i stadsmiljö med 40 förare har genomförts. Förarna valdes baserat på självskattad körstil (offensiv/defensiv) samt vana av att cykla i stadsmiljö (erfaren/oerfaren cyklist). Deltagarna exponerades flertalet gånger för tre situationer: sväng i korsning med interagerande cyklist, övergångställe med fotgängare, samt interaktion med andra motorfordon. Under försöket har data om hur förarna kör i förhållande till omgivningen och andra trafikanter, förarnas blickbeteende, förarnas arbetsbelastning, samt hur förarna interagerar med en icke-körrelaterad uppgift samlats in. Analyserna pågår i skrivande stund. Resultaten är därför avgränsade till situationen "korsning med interagerande cyklist".

Förarna stannade eller krypkörde innan de körde ut i korsningen i 254 av de 348 passagerna med högersväng och i 331 av 348 passager med vänstersväng. I många fall sökte försökspersonerna efter informationen för tidigt, t ex tittade försökspersonerna höger/vänster i korsningen när sikten fortfarande blockerades av kringliggande byggnader i 20% av passagerna. Beroende på kategori tittar mellan 50–80% av förarna i speglarna och/eller över axeln efter cyklister innan de svänger ut i korsningen. Den kategori som tittar oftast är de defensiva förarna som även är vana cyklister.

Högersvängsolyckor är ett vanligt scenario där cyklister blir påkörda. En trolig orsak är att förare inte söker av sina döda vinklar. Frågan är varför förare glömmer, eller inte ens känner till, att de behöver titta efter cyklister som kommer bakifrån. Våra preliminära resultat ger inga tydliga svar, mer än att bilister som även har erfarenhet av att cykla i stadstrafik är bättre på att samspela med cyklister.

Previous research has shown that drivers often fail to yield to cyclists who have the right of way, particularly when turning right. This finding was confirmed in a driving simulator study. To determine whether this is a systematic issue related to the type of attention required by road users, a systematic investigation was conducted.

When travelling through an intersection, different trajectories intersect. Various rules determine who has priority, resulting in different attention targets that road users must monitor to proceed safely and in accordance with the rules. For example, when going straight on a main road, the only attentional requirements on the driver are to monitor to the left and right for pedestrians who might want to cross on the zebra crossing. On a subordinate road in the same situation, the driver also needs to check for cross traffic from the left and from the right.  

The attention targets at intersections can be classified as either ‘overt’ (visible via signs, road markings, etc.) or ‘covert’ (unmarked and have to be remembered, e.g., the need to check ‘over the right shoulder’ for cyclists and pedestrians when a driver is turning right from a main road). Additionally, they can be categorised as ‘same-mass’ (for partners in an encounter) or ‘lower-mass’ (as in the turning-right example where the cyclist has lower mass), and as ‘required’ (when one must yield to superior traffic streams) or ‘not required’ (when one has priority).   

Conflicts arise when motor vehicles cross cycle paths during turns, often due to drivers neglecting over-the-shoulder glances. This paper examines the visual attention of car drivers at urban unsignalized intersections, considering turning direction, cross traffic, and cyclist approaching from behind.

A study with 44 participants was conducted using a fixed-base driving simulator equipped with an eXtended Reality (XR)-based visual system, which provided 360° immersion and enabled eye tracking for head movements and over-the-shoulder glances. Drivers were recruited based on urban cycling experience (inexperienced/experienced) and driving style (cautious/assertive). 

Results showed that in 47.8 % of intersection approaches, participants failed to adequately check for cyclists from behind. Driver characteristics did not consistently reveal traits associated with this neglect. Although cautious drivers with urban cycling experience made fewer mistakes, all groups were generally poor at checking for cyclists from behind. Post-drive questionnaire results on rule knowledge showed that, across participants, only half of the requirements to check for cyclists approaching from behind were indicated correctly. 

Drivers are more consistent in checking for cross-traffic, suggesting the neglect to check for cyclists is systemic rather than individual. The lack of awareness among drivers about their obligation to check for cyclists can be attributed to the less obvious nature of this traffic stream, as it comes from behind and lacks signs or warnings. Checking over the shoulder is physically more effortful, and cyclists may often pre-empt collisions, reinforcing drivers’ mental models to turn without checking. To improve safety, changes counteracting systemic biases against cyclists are needed.  

In most recent cases, motivated by the need to conduct tests in both physical and virtual test environment, a digital twin of the physical world is often created in the virtual environment to be used for testing purposes. This approach is often used in when testing automated driving systems (ADS) which are being extensively tested by companies and cities around the world. While this approach may work well with ADS, whose behaviour can be deterministic in both physical and virtual worlds, human drivers are known to exhibit different behaviour in simulation compared to real situations.

Since human drivers are still expected to be involved in future transport systems, the difference in driving behaviour needs to be understood in order to assist in verification and validation of the transport system. Therefore, in this work, we intend to investigate the differences in driving behaviour of human drivers, comparing the same manoeuvre done on the proving ground to the manoeuvre recorded in a driving simulator. 

Data collected from a proving ground will be compared with data collected from a driving simulator (under the same manoeuvre) to analyse differences in driving behaviour between the two test environments. More specifically, there are two datasets in this work: 1) data collected from AstaZero proving ground; and 2) data collected from the "Sim IV" driving simulator at VTI.

The difference between collected data will be analysed using statistical methods. The results indicating difference in driving behaviour between the two datasets will be presented. The results will be analysed and presented in the context of verification and validation of transport systems using digital twins.

This work intends to present the differences in driving behaviour of human drivers, comparing the same manoeuvre done on the proving ground to the manoeuvre recorded in a driving simulator. The result will provide some indication on the validity of using driving simulator as a virtual test environment for verification and validation of transport systems.

Automotive innovations are increasingly software-driven, necessitating frequent updates. Current validation processes heavily rely on physical testing, which is time-consuming and costly. The project focuses on how vehicle functionalities could be tested and validated in simulation models and what fidelity level that could be reached. By utilizing virtual environments, the project aims to proactively test software functions before deployment, ensuring accurate assessments of system performance in diverse scenarios.

The primary goal is to develop strategies that balance the realism of virtual test environments with practical implementation. Key research questions include:

• What level of realism is required for simulations to be credible for testing edge cases?
• How can virtual testing be integrated with real-world data to discover new edge cases?
• How can virtual testing ensure functional safety to satisfy regulatory bodies?

The project also seeks to establish metrics for comparing physical and virtual test results and to utilize open-source tools for broader industry use.

The project identified gaps between physical and simulated test results, such as differences in braking activations between physical test and simulation. It also highlighted the need for improving simulation tools' ability to replicate real-world vehicle behaviour accurately.

Key findings include:

• Virtual tests can be reliable but require tuning to achieve higher fidelity.
• Physical tests remain crucial for validating simulation models.
• Establishing standardized KPIs for virtual testing is essential to enhance credibility.

The project faced several challenges such as:

• Variability in sensor models across partners.
• Human factors introducing inconsistencies in physical tests.
• Limitations of existing simulation tools to accurately replicate real-world scenarios.

A comprehensive list of challenges was compiled to guide future research and development efforts.

EVIDENT successfully demonstrated the potential of virtual validation for ADAS and AD features. The project contributed to developing methodologies for comparing physical and virtual tests and provided insights into the requirements for credible virtual toolchains.

This article presents the results of a systematic literature review on the use of Intelligent Learning Systems (ILS) in simulator-based professional education contexts aiming to provide guidelines on how to design a personalized, flexible, and adaptive learning experience to be used in remote simulator training for maritime cadets. The PRISMA protocol was employed to identify empirical studies published in international academic journals between 2018–2023. In the first step, 782 records were identified through searching through Scopus and Web of Science. After screening abstracts and full texts, a total of 10 studies remained. The article synthesizes results from three different domains where ILS have been used for simulator-based professional training: social science education, healthcare, and transportation. The results show a wide variety of applications and approaches to ILS design, such as to enhancing motivation and satisfaction in the students’ learning process through adaptive feedback, or to provide real-time evaluations and feedback to trainees. The review shows the importance of considering end-user groups and how these may make use of the system in the design of an ILS. While systems can offer modules to both instructor and trainee, it is important to recognize that the two are different in terms of what is needed to facilitate an effective, efficient, and learner-centered training path.

På VTI har tre simulatorstudier genomförts under 2024 som använder sig av denna teknik. I dessa tre studier har utrustningen använts som körsimulator, simulator för gångare och simulator för cyklister. Vid byggandet av simulatorlösningarna så provades ett antal olika arbetssätt och inställningar för att sedan landa i hur studierna genomfördes. När studierna genomfördes så tillfrågades deltagarna i slutet av studierna om hur de tyckte det gick att använda utrustningen och om hur realistisk deras upplevelse var. Dessa svar har sedan analyserats och jämförts med historiska data från tidigare simulatorstudier.

Vid användning av ”green-screen” teknik för XR så har det varit viktigt med bra ljusförhållanden. För gångare användes extra ”trackers” för att ge ett tillfredsställande rörelsebeteende. Dessa ”trackers” behöver vara i kontakt med basstationer så med väldigt rörliga gångare kan fler basstationer behövas. XR systemen kräver mycket datorprestanda så det är viktigt att ha rätt hårdvara och en del optimering kan behövas för att få tillfredsställande prestanda. Vid långvarig användning så kan det vara bra att stänga av/starta om systemet då och då. Försökspersoner som har varit gångare eller cyklister beskriver en högre realism än förare även om alla tycker att det har varit realistiskt. Det fanns heller inga indikationer på en ökad simulatorsjuka och för cyklister så rapporterades den lägsta simulatorsjukan. De flesta tyckte att det gick bra att använda ett headset och tyckte inte att det var speciellt besvärande. Att kunna se detaljer i miljön verkar ligga på samma nivå som med skärmar.

Från dessa studier så kan vi se att huvudbaserade XR/VR lösningar ger ytterligare möjligheter till simulatorstudier och kompletterar på så sätt skärmbaserade simulatorer. En fördel är att de ger en friare känsla av att röra sig och kunna titta runt samtidigt som de kan spåra var försökspersoner tittar. En nackdel är att de är prestandakrävande vilket ger en utmaning i att skapa väldigt levande miljöer. Sammanfattningsvis så kommer VTI fortsatt att använda tekniken.

Performing a non-driving related activity (NDRA) is often equated with being distracted. While it may seem pedagogically sound to discourage any form of NDRA, this approach can have the opposite effect. If drivers find that they can engage in an NDRA without negative consequences in some situations, they may incorrectly generalise this behaviour and assume that their driving is sufficiently good to perform NDRAs also in other more demanding situations. Eventually, this may lead to drivers underestimating the risks of inattention. The MiRA theory defines “attention” as when a road user samples information from all required target areas in a specific situation in a timely manner. If the road user has the spare capacity to perform other tasks, they would still be considered “attentive.” However, if not all required areas are sampled, the road user would be classified as “inattentive” in that situation, regardless of whether they are performing an NDRA. The objective of this study was to investigate whether drivers integrate a partially self-paced NDRA into urban driving with varying attentional requirements, and whether one’s self-reported driving style and cycling experience affects this.