用强化学习个性化提醒，减少干扰同时提升监控效率。
Intelligent support for Human Oversight: Integrating Reinforcement Learning with Gaze Simulation to Personalize Highlighting
- 结合用户注视模拟，让AI在无真实部署下学习最优提醒策略
- 实验显示该方法比固定规则提醒更有效，降低认知负担
- 适合需要实时监控的高压力场景，如无人机调度
在时间紧迫的监控场景中，人机协同界面需有效支持用户的情境感知。本文探索基于强化学习（RL）的UI自适应机制，以个性化调整提醒策略，在突出关键事件与减少干扰之间取得平衡。为避免真实部署风险，研究引入用户注视行为模型，模拟监控过程中的注意力动态。通过配送无人机监督任务的实验，初步结果表明，基于强化学习的提醒方式优于静态规则方法，同时揭示了智能监督支持面临的技术挑战。
原文摘要 · Abstract (English)
Interfaces for human oversight must effectively support users' situation awareness under time-critical conditions. We explore reinforcement learning (RL)-based UI adaptation to personalize alerting strategies that balance the benefits of highlighting critical events against the cognitive costs of interruptions. To enable learning without real-world deployment, we integrate models of users' gaze behavior to simulate attentional dynamics during monitoring. Using a delivery-drone oversight scenario, we present initial results suggesting that RL-based highlighting can outperform static, rule-based approaches and discuss challenges of intelligent oversight support.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。