Mark Colley

Ding Xia, Xinyue Gui, Mark Colley et al.

Automated vehicles lack natural communication channels with other road users, making external Human-Machine Interfaces (eHMIs) essential for conveying intent and maintaining trust in shared environments. However, most eHMI studies rely on developer-crafted message-action pairs, which are difficult to adapt to diverse and dynamic traffic contexts. A promising alternative is to use Large Language Models (LLMs) as action designers that generate context-conditioned eHMI actions, yet such designers lack perceptual verification and typically depend on fixed prompts or costly human-annotated feedback for improvement. We present See2Refine, a human-free, closed-loop framework that uses vision-language model (VLM) perceptual evaluation as automated visual feedback to improve an LLM-based eHMI action designer. Given a driving context and a candidate eHMI action, the VLM evaluates the perceived appropriateness of the action, and this feedback is used to iteratively revise the designer's outputs, enabling systematic refinement without human supervision. We evaluate our framework across three eHMI modalities (lightbar, eyes, and arm) and multiple LLM model sizes. Across settings, our framework consistently outperforms prompt-only LLM designers and manually specified baselines in both VLM-based metrics and human-subject evaluations. Results further indicate that the improvements generalize across modalities and that VLM evaluations are well aligned with human preferences, supporting the robustness and effectiveness of See2Refine for scalable action design.

Simon Lämmer, Mark Colley, Patrick Ebel

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.

Mark Colley, Sebastian Pickl, Frank Uhlig et al.

The automation of the driving task affects both the primary driving task and the automotive user interfaces. The liberation of user interface space and cognitive load on the driver allows for new ways to think about driving. Related work showed that activities such as sleeping, watching TV, or working will become more prevalent in the future. However, social aspects according to Maslow's hierarchy of needs have not yet been accounted for. We provide insights of a focus group with N=5 experts in automotive user experience revealing current practices such as social need fulfillment on journeys and sharing practices via messengers and a user study with N=12 participants of a first prototype supporting these needs in various automation levels showing good usability and high potential to improve user experience.

Mark Colley, Marcel Walch, Enrico Rukzio

Automated vehicles can implement strategies to drive with optimized fuel efficiency. Therefore, automated driving is seen as a major advancement in tackling climate change. However, with automated vehicles driving in cities and other areas rife with other road users such as human drivers, pedestrians, or cyclists, there is the potential for "stop-and-go" traffic. This would greatly diminish the possibility of automated vehicles to drive fuel-efficient. We suggest using external communication of automated vehicles to aid in ecological driving by providing clues to other road users to show the intent and therefore ultimately enable smoother traffic.