How do drivers interact with In-Vehicle Information Systems (IVIS)? Driver distraction is one of the major contributors to road crashes, and IVIS interactions are a potential source of such distraction. Yet, little is known about when, how, and under which driving contexts drivers engage with IVIS in everyday driving. However, for safe system design and evidence-based regulation, we must understand which context factors shape IVIS engagement. To close this gap, we leverage large-scale naturalistic data collected from 669,493 customer trips across 79 countries, to characterize everyday IVIS interactions. Using mixed-effects models, we examine how environmental conditions, vehicle dynamics, road infrastructure, driving automation, and vehicle mileage affect how drivers engage with IVISs. Our results show that drivers interact approximately every five minutes, mostly at the start of their trip, and more frequently via physical buttons than touchscreen inputs. We further observe significant regional differences in how IVISs are used and show that engagement decreases with vehicle mileage. In partially automated conditions, drivers are more likely to initiate interactions, while increased driving dynamics lead to fewer and less complex engagements. Together, these findings extend existing evidence by demonstrating how multiple contextual factors simultaneously shape real-world IVIS engagement. They provide an empirical basis for context-aware IVIS design, evaluation, and regulation that more accurately reflects the diversity and variability of everyday driving behavior.

People's transportation choices reflect complex trade-offs shaped by personal preferences, social norms, and technology acceptance. Predicting such behavior at scale is a critical challenge with major implications for urban planning and sustainable transport. Traditional methods use handcrafted assumptions and costly data collection, making them impractical for early-stage evaluations of new technologies or policies. We introduce Generative Traffic Agents (GTA) for simulating large-scale, context-sensitive transportation choices using LLM-powered, persona-based agents. GTA generates artificial populations from census-based sociodemographic data. It simulates activity schedules and mode choices, enabling scalable, human-like simulations without handcrafted rules. We evaluate GTA in Berlin-scale experiments, comparing simulation results against empirical data. While agents replicate patterns, such as modal split by socioeconomic status, they show systematic biases in trip length and mode preference. GTA offers new opportunities for modeling how future innovations, from bike lanes to transit apps, shape mobility decisions.

Designing mobile and interactive technologies requires understanding how users sample dynamic environments to acquire information and make decisions under time pressure. However, existing computational user models either rely on hand-crafted task representations or are limited to static or non-interactive visual inputs, restricting their applicability to realistic, pixel-based environments. We present CR-Eyes, a computationally rational model that simulates visual sampling and gameplay behavior in Atari games. Trained via reinforcement learning, CR-Eyes operates under perceptual and cognitive constraints and jointly learns where to look and how to act in a time-sensitive setting. By explicitly closing the perception–action loop, the model treats eye movements as goal-directed actions rather than as isolated saliency predictions. Our evaluation shows strong alignment with human data in task performance and aggregate saliency patterns, while also revealing systematic differences in scanpaths. CR-Eyes is a step toward scalable, theory-grounded user models that support design and evaluation of interactive systems.

In many work environments, operators must monitor multiple information sources, quickly identify critical situations, and respond appropriately. Attention Management Systems (AMS) are designed to help users coordinate attention in such contexts. However, while most AMS research has focused on multitasking and task-switching, their potential to guide gaze in dynamic monitoring remains unexplored. To address this, we evaluated two AMS designs in a controlled experiment (n=15) using Senders Dial Task: Ambient Cues and a dynamic Gaze Bubble. Although participants were more likely to follow the moving Gaze Bubble, this design led to significantly poorer performance compared to Ambient Cues and a control group without AMS assistance. Our findings show that while AMS design influences visual attention, suboptimal designs can impair task performance. Further research is needed to identify design parameters that guide attention effectively while supporting performance.

The transition to mixed-traffic environments that involve automated vehicles, manually operated vehicles, and vulnerable road users presents new challenges for human-centered automotive research. Despite this, most studies in the domain focus on single-agent interactions. This paper reports on a participatory workshop (N = 15) and a questionnaire (N = 19) conducted during the AutomotiveUI '24 conference to explore the state of multi-agent automotive research. The participants discussed methodological challenges and opportunities in real-world settings, simulations, and computational modeling. Key findings reveal that while the value of multi-agent approaches is widely recognized, practical and technical barriers hinder their implementation. The study highlights the need for interdisciplinary methods, better tools, and simulation environments that support scalable, realistic, and ethically informed multi-agent research.

Total precipitation is a key variable of the weather state, accumulated over a given period. Beyond their direct relevance, high-quality precipitation data are of importance for driving downstream applications in hydrology, e.g. river streamflow and runoff forecasting. However, common measurements of precipitation are either precise but sparse (as for in-situ recordings) or global but uncertain (as for spaceborne observations). Though reanalysis products such as ECMWF’s ERA5 provide a best estimate of the state of the atmosphere, the quality of their total precipitation reconstruction is imperfect. Following reports that ERA5 is prone to overestimating the occurrence of drizzle at the cost of underestimating extreme precipitation, prior work explored data-driven models for local post-processing to address the latter. However, the local models employed in preceding work do not easily extend to a global post-processing setup and an exclusive emphasis on outliers limits the ability to represent the full distribution of precipitation intensity, which limits their relevance. In this work, we propose a novel approach for precipitation post-processing which models the entire globe in a single forward pass and models dryness, light rain and heavy rain alike. The post-processer is based on a graph neural network architecture, trained on decades of gauge-calibrated multi-source weighted estimates of precipitation. We demonstrate that our model learns to bias-correct ERA5 total precipitation information and consistently improves upon the baseline while maintaining its global applicability. Further experiments will detail the nature of its improvements and may explore its benefits for downstream applications.

How do drivers perceive risk? Understanding what situations and factors cause drivers to perceive situations as critical can improve our understanding of road user behavior and inform automated driving technology. To investigate the factors that shape drivers’ risk perception, we conducted an eye-tracking study with 27 participants who watched dashcam videos and continuously rated the perceived risk of various driving situations. Using the resulting dataset, we developed a computer vision-based machine learning approach that generates explainable predictions of perceived risk from video and eye-tracking data. Our SHAP analysis reveals that the proximity of objects and number of cars in a scene are the most significant contributors to perceived risk. Most interestingly, while people tend to sample similar objects in critical situations, their risk perception remains highly personal making visual sampling behavior a weak predictor of perceived risk. Overall, our explanations reveal non-linear insights beyond previous work, suggesting that risk perception is not only shaped by visual input, but primarily by cognitive processes which is in line with theoretical models of situation awareness.

Modern driving involves interactive technologies that can divert attention, increasing the risk of accidents. This paper presents a computational cognitive model that simulates human multitasking while driving. Based on optimal supervisory control theory, the model predicts how multitasking adapts to variations in driving demands, interactive tasks, and automation levels. Unlike previous models, it accounts for context-dependent multitasking across different degrees of driving automation. The model predicts longer in-car glances on straight roads and shorter glances during curves. It also anticipates increased glance durations with driver aids such as lane-centering assistance and their interaction with environmental demands. Validated against two empirical datasets, the model offers insights into driver multitasking amid evolving in-car technologies and automation.

Geospatial foundation models (GFMs) for Earth observation often fail to perform reliably in environments underrepresented during pretraining. We introduce SHRUG-FM, a framework for reliability-aware prediction that enables GFMs to identify and abstain from likely failures. Our approach integrates three complementary signals: geophysical out-of-distribution (OOD) detection in the input space, OOD detection in the embedding space, and task-specific predictive uncertainty. We evaluate SHRUG-FM across three high-stakes rapid-mapping tasks: burn scar segmentation, flood mapping, and landslide detection. Our results show that SHRUG-FM consistently reduces prediction risk on retained samples, outperforming established single-signal baselines like predictive entropy. Crucially, by utilizing a shallow "glass-box" decision tree for signal fusion, SHRUG-FM provides interpretable abstention thresholds. It builds a pathway toward safer and more interpretable deployment of GFMs in climate-sensitive applications, bridging the gap between benchmark performance and real-world reliability.

In this workshop, we invite researchers, designers, and practitioners to explore together how life-cycle thinking can contribute to the design of intelligent, sustainable mobility solutions. While current research primarily focuses on making the usage period of such solutions more sustainable, we aim to take a broader perspective by integrating sustainability from the earliest design stages through to the end of the vehicle’s life. Therefore, we will use speculative and critical design thinking to inspire and explore challenges as well as opportunities concerning sustainability at every stage of the life-cycle, from Design and Production to Usage, and End-Of-Life. Next, we will lead an ideation and prototyping session, followed by an interdisciplinary discussion reflecting on how intelligent technology can promote sustainable mobility. The outcomes will include potential design ideas and future research directions for incorporating life-cycle considerations into future mobility solutions.

Urban Air Mobility (UAM) emerges as a potential solution to urban congestion. However, as it lacks integration with existing transportation systems, methods to study its impact are necessary. Traditional empirical approaches are insufficient to study large-scale effects in this not-yet-real context. We developed UAM-SUMO, an extension of the SUMO simulation platform, to simulate the impact of UAM on public transportation, particularly how air taxis affect traffic flow and mode choices. We detail the modifications to SUMO and the UAM operation parameters. We open-source our code at https://github.com/M-Colley/uam-sumo and present a proof-of-concept data collection and analysis for Ingolstadt, Germany.

This report summarises the main outcomes of the 4th edition of the workshop on Machine Learning (ML) for Earth System Observation and Prediction (ESOP / ML4ESOP) co-organised by the European Space Agency (ESA) and the European Centre for Medium-Range Weather Forecasts (ECMWF). The 4-day workshop was held on 7-10 May 2024 in a hybrid format at the ESA Frascati site with an interactive online component, featuring over 46 expert talks with a record number of submissions and about 800 registrations. The workshop offered leading experts a platform to exchange on the current opportunities, challenges and future directions for applying ML methodology to ESOP. To structure the presentations and discussions, the workshop featured five main thematic areas covering key topics and emerging trends. The most promising research directions and significant outcomes were identified by each thematic area’s Working Group and are the focus of this document.

In this review, we analyze the current state of the art of computational models for in-vehicle User Interface (UI) design. Driver distraction, often caused by drivers performing Non Driving Related Tasks (NDRTs), is a major contributor to vehicle crashes. Accordingly, in-vehicle UI s must be evaluated for their distraction potential. Computational models are a promising solution to automate this evaluation, but are not yet widely used, limiting their real-world impact. We systematically review the existing literature on computational models for NDRTs to analyze why current approaches have not yet found their way into practice. We found that while many models are intended for UI evaluation, they focus on small and isolated phenomena that are disconnected from the needs of automotive UI designers. In addition, very few approaches make predictions detailed enough to inform current design processes. Our analysis of the state of the art, the identified research gaps, and the formulated research potentials can guide researchers and practitioners toward computational models that improve the automotive UI design process.

We review the state of open science and the perspectives on open data sharing within the automotive user research community. Openness and transparency are critical not only for judging the quality of empirical research, but also for accelerating scientific progress and promoting an inclusive scientific community. However, there is little documentation of these aspects within the automotive user research community. To address this, we report two studies that identify (1) community perspectives on motivators and barriers to data sharing, and (2) how openness and transparency have changed in papers published at AutomotiveUI over the past 5 years. We show that while open science is valued by the community and openness and transparency have improved, overall compliance is low. The most common barriers are legal constraints and confidentiality concerns. Although research published at AutomotiveUI relies more on quantitative methods than research published at CHI, openness and transparency are not as well established. Based on our findings, we provide suggestions for improving openness and transparency, arguing that the motivators for open science must outweigh the barriers. All supporting materials are freely available at: https://osf.io/zdpek/

To increase trust in systems, engineers strive to create explanations that are as accurate as possible. However, if the system's accuracy is compromised, providing explanations for its incorrect behavior may inadvertently lead to misleading explanations. This concern is particularly pertinent when the correctness of the system is difficult for users to judge. In an online survey experiment with 162 participants, we analyze the impact of misleading explanations on users' perceived and demonstrated trust in a system that performs a hardly assessable task in an unreliable manner. Participants who used a system that provided potentially misleading explanations rated their trust significantly higher than participants who saw the system's prediction alone. They also aligned their initial prediction with the system's prediction significantly more often. Our findings underscore the importance of exercising caution when generating explanations, especially in tasks that are inherently difficult to evaluate. The paper and supplementary materials are available at https://doi.org/10.17605/osf.io/azu72.

Cloud removal (CR) is a significant and challenging problem in remote sensing, and in recent years, there have been notable advancements in this area. However, two major issues remain hindering the development of CR: the unavailability of high-resolution imagery for existing datasets and the absence of evaluation regarding the semantic meaningfulness of the generated structures. In this article, we introduce M3R-CR, a benchmark dataset for high-resolution CR with multimodal and multiresolution data fusion. M3R-CR is the first public dataset for CR to feature globally sampled high-resolution optical observations, paired with radar measurements and pixel-level land-cover annotations. With this dataset, we consider the problem of CR in high-resolution optical remote-sensing imagery by integrating multimodal and multiresolution information. In this context, we have to take into account the alignment errors caused by the multiresolution nature, along with the more pronounced misalignment issues in high-resolution images due to inherent imaging mechanism differences and other factors. Existing multimodal data fusion-based methods, which assume the image pairs are aligned accurately at the pixel level, are thus not appropriate for this problem. To this end, we design a new baseline named Align-CR to perform the low-resolution synthetic aperture radar (SAR) image-guided high-resolution optical image CR. It gradually warps and fuses the features of the multimodal and multiresolution data during the reconstruction process, effectively mitigating concerns associated with misalignment. In the experiments, we evaluate the performance of CR by analyzing the quality of visually pleasing textures using image reconstruction (IR) metrics and further analyze the generation of semantically meaningful structures using a well-established semantic segmentation task. The proposed Align-CR method is superior to other baseline methods in both areas. The project is available at https://gitlab.lrz.de/ai4eo/M3R-CR.

In the future, roads will host a complex mix of automated and manually operated vehicles, along with vulnerable road users. However, most automotive user interfaces and human factors research focus on single-agent studies, where one human interacts with one vehicle. Only a few studies incorporate multi-agent setups. This workshop aims to (1) examine the current state of multi-agent research in the automotive domain, (2) serve as a platform for discussion toward more realistic multi-agent setups, and (3) discuss methods and practices to conduct such multi-agent research. The goal is to synthesize the insights from the AutoUI community, creating the foundation for advancing multi-agent traffic interaction research.

Floods are among the most common and devastating natural hazards, imposing immense costs on our society and economy due to their disastrous consequences. Recent progress in weather prediction and spaceborne flood mapping demonstrated the feasibility of anticipating extreme events and reliably detecting their catastrophic effects afterwards. However, these efforts are rarely linked to one another and there is a critical lack of datasets and benchmarks to enable the direct forecasting of flood extent. To resolve this issue, we curate a novel dataset enabling a timely prediction of flood extent. Furthermore, we provide a representative evaluation of state-of-the-art methods, structured into two benchmark tracks for forecasting flood inundation maps i) in general and ii) focused on coastal regions. Altogether, our dataset and benchmark provide a comprehensive platform for evaluating flood forecasts, enabling future solutions for this critical challenge. Data, code models are shared at https://github.com/Multihuntr/GFF under a CC0 license.

Hurricanes and coastal floods are among the most disastrous natural hazards. Both are intimately related to storm surges, as their causes and effects, respectively. However, the short-term forecasting of storm surges has proven challenging, especially when targeting previously unseen locations or sites without tidal gauges. Furthermore, recent work improved short and medium-term weather forecasting but the handling of raw unassimilated data remains non-trivial. In this paper, we tackle both challenges and demonstrate that neural networks can implicitly assimilate sparse in situ tide gauge data with coarse ocean state reanalysis in order to forecast storm surges. We curate a global dataset to learn and validate the dense prediction of storm surges, building on preceding efforts. Other than prior work limited to known gauges, our approach extends to ungauged sites, paving the way for global storm surge forecasting.