CISE-MSI: DP: SaTC: Dynamically Enforcing User-Oriented Geospatial Restrictions for Drone Fly-Overs

该奖项全部或部分根据2021年美国救援计划法案（公法117-2）资助。无人驾驶飞机，最近在商业和娱乐用途上变得非常流行。然而，目前还没有有效的解决方案来限制无人机飞越敏感空间，如家庭、学校、医院、临时限制区域等，无论是作为最终目的地还是在运输途中。这引起了与以下方面有关的严重关切：（i）隐私，例如，无人机在未经明确同意的情况下拍照和/或录制视频;（ii）网络安全，例如，无人机用作发动网络攻击的平台;（iii）安全，例如，无人机碰撞，可能会导致人为影响和财务成本。为了解决这些问题，该项目正在开发禁飞区，这是一个规范无人机飞越的开源框架，提供了以下手段：㈠确定和划定敏感的物理空间; ㈡具体规定和执行对无人机飞行的限制; ㈢计算无人机飞越敏感空间的飞行计划; ㈣通过协调飞行计划限制无人机空域占用。最终，禁飞区涉及一个尖端的研究议程，对教育，公共和商业利益产生影响，并向管理机构通报国家空域系统中的无人机操作。为实现上述目标，禁飞区采用了新的方法：㈠利用光探测和测距（激光雷达）和干涉合成孔径雷达（干涉合成孔径雷达）对敏感空间的保护区进行建模和划界; ㈡利用属性和空间敏感访问控制，理解和编写所谓的飞越政策;（iii）通过利用基于分布式哈希表的云架构来存储、检索和评估飞越策略;（iv）通过利用多标准决策（MCDM）和帕累托前沿（PF）对功耗、有效载荷能力、环境参数、保护区和立交桥政策;（v）通过安全气泡编排导航计划，利用感知与规避（SAA）和超视距（BVLOS）来模拟基于天气条件、占用限制、人口密度的风险，该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).Unmanned aircraft systems, a.k.a. drones, have recently become quite popular for commercial and recreational purposes. However, no effective solutions exist to restrict drones from flying over sensitive spaces such as homes, schools, hospitals, temporally-restricted areas, etc., either as final destinations or while in-transit. This introduces serious concerns related to: (i) privacy, e.g., drones taking pictures and/or record video without explicit consent; (ii) cyber-security, e.g., drones used as platforms for launching cyberattacks; (iii) safety, e.g., drone collisions that may result in human affectations and financial costs. To address these concerns, this project is developing No-Fly-Zone, an open-source framework that regulates drone fly-overs by providing the means to: (i) identify and delimit sensitive physical spaces; (ii) specify and enforce restrictions on drone flights; (iii) calculate flight plans for drones passing over sensitive spaces; (iv) limit airspace drone occupancy by orchestrating flight plans. Ultimately, No-Fly-Zone involves a cutting-edge research agenda that has an impact across educational, public, and commercial interests, and informs governing agencies on drone operations in the National Airspace System. To achieve the goals just mentioned, No-Fly-Zone introduces novel methodologies for: (i) modeling and delimiting protection zones over sensitive spaces by leveraging Light Detection and Ranging (lidar) and Interferometric Synthetic Aperture Radar (InSAR); (ii) understanding and writing so-called fly-over policies by leveraging Attributes and Space-Sensitive Access Control; (iii) storing, retrieving, and evaluating fly-over policies by leveraging a cloud architecture based on Distributed Hash Tables; (iv) developing navigation plans for drones by leveraging Multi-Criteria Decision Making (MCDM) and Pareto Front (PF) to model power consumption, payload capabilities, environmental parameters, protected zones, and fly-over policies; (v) orchestrating navigation plans by means of safety bubbles, which leverage Sense and Avoid (SAA) and Beyond Visual Line-of-Sight (BVLOS) to model risks based on weather conditions, occupancy limits, population density, etc.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.