Attention management systems aim to mitigate the negative effects of multitasking. However, sophisticated real-time attention management is yet to be developed. We present a novel concept for attention management with reinforcement learning that automatically switches tasks. The system was trained with a user model based on principles of computational rationality. Due to this user model, the system derives a policy that schedules task switches by considering human constraints such as visual limitations and reaction times. We evaluated its capabilities in a challenging dual-task balancing game. Our results confirm our main hypothesis that an attention management system based on reinforcement learning can significantly improve human performance, compared to humans’ self-determined interruption strategy. The system raised the frequency and difficulty of task switches compared to the users while still yielding a lower subjective workload. We conclude by arguing that the concept can be applied to a great variety of multitasking settings.

Studies across various task types suggest that collaboration between humans and AI leads to improved and more satisfying outcomes. However, the effects of prolonged use of AI on users’ skills and perceptions remain unclear. This study involved 12 participants using an AI-based assistant in a multitasking balancing game over five days. Our findings indicate that AI assistance improved participants’ performance, even for the condition that was not supported by AI, showing no deskilling effect. Additionally, participants experienced significantly lower cognitive load (measured via ocular pupil diameter) in the AI-supported condition. This suggests that AI-assisted training can enhance multitasking motor skills in a less stressful and cognitively demanding manner. We also found a positive correlation between users’ understanding of the AI assistant and its acceptance, highlighting the importance of transparency and effectively communicating the capabilities of AI applications.

Appropriate monitoring and successfully intervening when automation fails is one of the most critical issues in level 2 automated driving, since drivers suffer from low situation awareness when using such systems. To counter, we present a gamified in-vehicle interface based on ideas from previous work, where drivers have to support the vehicle by pointing at other traffic objects in the environment. We hypothesized that this system could help drivers in the monitoring task, maintain their situation awareness, and result in lower crash rates. We implemented a prototype of this system and evaluated it in a lab study with N=20 participants. The results indicate that participants were looking more intensively at lead vehicles and performed stronger braking actions. However, there was no measurable benefit on situation awareness and intervention performance in critical situations. We conclude by discussing differences to related experiments and present future ideas.

Attention management systems seek to minimize disruption by intelligently timing interruptions and helping users navigate multiple tasks and activities. While there is a solid theoretical basis and rich history in HCI research for attention management, little progress has been made regarding their practical implementation and deployment. Building sophisticated attention management systems requires a great variety of sensors, task- and user models, and multiple devices while considering the complexity of user context and human behavior. Novel AI technologies, such as generative systems, reinforcement learning, and large language models, open new possibilities to create intelligent, practical, and user-centered attention management systems. This proposed workshop aims to bring together researchers and practitioners from diverse backgrounds to discuss and formulate a research agenda to advance attention management systems using novel AI tools to manage and mitigate interruptions from computing systems effectively.

Notifications and interruptions have shown to significantly impede task performance while causing stress. Attention management systems aim at mitigating these negative effects, for example, by delaying interruptions to task boundaries or times of low mental load. However, while the theoretical benefits of such an approach are well-documented, it is quite unclear how holding back information from users is accepted, especially in times of the “always-on-mentality”. Thus, we conducted an online vignette experiment with N=163 participants, who were presented hypothetical private and work-related scenarios where interruptions are delayed by attention management systems. Participants rated how long they would allow particular interruptions to be delayed, as well as which data collection methods a system could use to perform these decisions. Our results show that interruption management is desired by potential users, provided they feel in control. We conclude with recommendations for the design of attention management systems.