We investigate personalised feedback mechanisms to help drivers regulate their emotions, aiming to improve road safety. We systematically evaluate driver-preferred feedback modalities and their impact on emotional states. Using unobtrusive vision-based emotion detection and self-labeling, we captured the emotional states and feedback preferences of 21 participants in a simulated driving environment. Results show that in-car feedback systems effectively influence drivers’ emotional states, with participants reporting positive experiences and varying preferences based on their emotions. We also developed a machine learning classification system using facial marker data to demonstrate the feasibility of our approach for classifying emotional states. Our contributions include design guidelines for tailored feedback systems, a systematic analysis of user reactions across three feedback channels with variations, an emotion classification system, and a dataset with labeled face landmark annotations for future research.
Automated vehicles (AVs) could transform commute time into learning opportunities by freeing passengers from driving tasks. We conducted semi-structured interviews with 31 regular commuters, including educators and automotive experts, to identify design challenges and opportunities for AV-based learning. Using general inductive thematic analysis, we identified three key challenges: managing cognitive load and distraction, technology integration and privacy, and content design and interdisciplinary alignment. We also identified four autonomous vehicle-specific opportunities: journey-linked contextual learning, productive time utilization, controlled sensory environments, and automation-aware personalization. Our findings indicate that AV affordances, including real-time environmental data, private space, and extended uninterrupted time, create design requirements distinct from general mobile learning. We contribute design recommendations for adaptive focus management, context-aware content delivery, multi-modal interaction, and privacy-preserving personalization to guide future AV learning systems.