Investigation of how communication should adapt to event priority and passenger activity highlights event consequence, passenger activity, continuing information value, and confirmation need as key considerations for selective in-cabin communication.
Abstract
Proactive in-cabin agents can help passengers understand automated-vehicle (AV) behavior, but communicating every ride event may introduce unnecessary interruptions. We investigated how communication should adapt to event priority and passenger activity. In a mixed-methods within-subject study, 41 participants rode as passenger in a VR simulated fully-automated vehicle. We compared an event-triggered (ET) policy that communicated immediately at every event with a context-sensitive (CS) policy that selected \textit{Immediate}, \textit{Delayed}, or \textit{Silent} communications. CS increased communication appropriateness and substantially reduced perceived interruption. Perceived trust did not differ between policies, although baselines dispositional trust differentiated communication preferences. Findings highlight event consequence, passenger activity, continuing information value, and confirmation need as key considerations for selective in-cabin communication.
Current AI-based conversational agents (CAs) largely lack situational awareness, limiting their ability to understand driving context, driver state, and immediate driver needs. Consequently, the use of CA may increase drivers’ cognitive load and impair safety and user experience. This study investigates the role of sit...
Johanna Vännström, Andreas Absér, Jacob Weilandt et al.· Adjunct Proceedings of the 1...· 0 citations
While conversational AI agents (CAs) have the potential to support drivers through hands-free and eyes-free interaction, their role in long-haul trucking remains unexplored. This paper investigates how long-haul truck drivers perceive CAs and identifies design considerations for their successful deployment. We conducte...
Johanna Vännström, Andreas Absér, Azra Habibovic et al.· Adjunct Proceedings of the 1...· 0 citations
Proactive LLM agents can turn idle compute into useful support before users ask. Yet even correct work can misread user context, impose review costs, or undermine trust. This work proposes foundations for designing, realizing, and evaluating proactive LLM agents around three joint principles (3T): Task Capability, anti...
Jio Oh, Seunghyun Do, Young-Jun Lee et al.· 0 citations
Human-automated vehicle (AV) interaction can be understood as a form of teaming because safe driving often depends on coordinated contributions from both the driver and automation. Although AVs are often framed as reducing human involvement, many dynamic scenarios still require drivers and automated systems to coordina...
Jing Zang, Brandon J. Pitts· Proceedings of the Human Fac...· 0 citations
This work proposes an always-on attention-coordination layer that mediates this interface and allocates human attention across one or more working agents, and introduces JarvisBench to evaluate both directions of this coordination.
The findings suggest that the primary benefit of human--agent interfaces may be reducing interaction effort rather than improving speed, and that delegation reflects who the user is more than what the task demands.
Gavin Raine Dizon, Tyrone Justin Sta Maria, J. A. Deja et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 28, 2026
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
