Passive fatigue during conditional automated driving can compromise driver readiness and safety. This paper presents findings from a test-track study with 40 participants in a real-world automated driving scenario. In this scenario, a Large Language Model (LLM) based conversational agent (CA) was designed to check in with drivers and re-engage them with their surroundings. Drawing on in-car video recordings, sleepiness ratings and interviews, we analysed how drivers interacted with the agent and how these interactions shaped alertness. Results show the CA is helpful for supporting vigilance during passive fatigue. Thematic analysis of acceptability further revealed three user preference profiles that implicate future intention to use CAs. Positioning empirically observed profiles within existing CA archetype frameworks highlights the need for adaptive design sensitive to diverse user groups. This work underscores the potential of CAs as proactive Human–Machine Interface (HMI) interventions, demonstrating how natural language can support context-aware interaction during automated driving.

The emergence of automated vehicles (AVs) introduces new challenges to human-vehicle interactions, especially in conditional automated driving.This study presents different head-up display designs as the human-machine interface (HMI) to convey uncertainty to AV users.It investigates the impact of such designs on drivers' physiological responses-via electrodermal activity data-and subjective evaluations of cognitive workload during the automated drive.A between-subjects driving simulator experiment (N=187) was conducted to examine four conditions: baseline (no HMI), a progressive colour-based Guardian Angel display, a text-based interruption, and a combination approach.The results showed significant effects of the presence of the Guardian Angel display interventions on physiological arousal associated with cognitive workload.However, the subjective ratings showed no difference across conditions.These findings indicate that the designed displays can trigger physiological responses without affecting perceived workload.It offers

Figure 1: Using vestibular cues as a subtle awareness "nudge" modality in L3 automated driving scenario.

This paper reports results from a high-fidelity driving simulator study (N=215) about a head-up display (HUD) that conveys a conditional automated vehicle’s dynamic “uncertainty” about the current situation while fallback drivers watch entertaining videos. We compared (between-group) three design interventions: display (a bar visualisation of uncertainty close to the video), interruption (interrupting the video during uncertain situations), and combination (a combination of both), against a baseline (video-only). We visualised eye-tracking data to conduct a heatmap analysis of the four groups’ gaze behaviour over time. We found interruptions initiated a phase during which participants interleaved their attention between monitoring and entertainment. This improved monitoring behaviour was more pronounced in combination compared to interruption, suggesting pre-warning interruptions have positive effects. The same addition had negative effects without interruptions (comparing baseline & display). Intermittent interruptions may have safety benefits over placing additional peripheral displays without compromising usability.

Takeover safety is a critical issue when using Level 2 advanced driver assistance systems. Understanding the context of takeover can facilitate the development of driver monitoring systems that can adapt to changing environments for more contextually appropriate assistance during takeover. The paper presents a hierarchical clustering analysis of hundreds of post-takeover vehicle kinematics in the MIT-AVT naturalistic driving study. Results show similar types of takeovers between Super Cruise and Autopilot: normal takeover, braking takeover, accelerating takeover, evasive-manoeuvre takeover, and right-swerve takeover (Autopilot only). Context analysis showed that braking takeover which occurred at a normal highway speed was often associated with upcoming highway exits and foreseeable low-speed situations, while accelerating, evasive-manoeuvre, and right-swerve takeovers were caused by strong brake (for Super Cruise) or large steering (for Autopilot) during slow car following. The findings indicate the potential for sensor-based approaches to assessing various contexts and facilitating a more holistic takeover reference model.

Driver fatigue and distraction are major road safety issues globally; developing driver state detection and warning technology to help reduce impairment-related incidents is a promising approach. The aim of this case study was to design an effective Human Machine Interface (HMI) for a near-market driver warning system primarily aimed at commercial truck driving. A human-centered design (HCD) process was employed for the development and evaluation. Application of HCD here was a multi-stage iterative process: a comprehensive literature review; developing a context of use description; undertaking truck driver interviews; identifying user needs and associated design requirements; conducting two design workshops; operationalizing the design; running HMI evaluation studies, and finalizing the HMI concepts. As a result of the iterative HCD process, the HMI comprises a multi-modal warning system (visual, auditory and tactile) with two levels for driver fatigue and an escalating system for driver distraction. Following this successful HCD process, further on-road evaluation work is proposed before the final version of the HMI is manufactured.