Towards using Unmanned Aerial Vehicles (UAVs) in Wilderness Search and Rescue Lessons from field trials
Towards using Unmanned Aerial Vehicles (UAVs) in Wilderness Search and Rescue Lessons from field trials
复制标题
DOI：
10.1075/is.10.3.08goo
复制
发表时间：
2009-01-01
影响因子：
1.5
通讯作者：
Adams, Julie A.
中科院分区：
文献类型：
--
作者：
Goodrich, Michael A.;Morse, Bryan S.;Adams, Julie A.
Wilderness Search and Rescue（WiSAR）是寻找和帮助在偏远荒野地区迷路的人的过程。由于这些地区通常崎岖或相对难以进入，寻找失踪人员可能需要大量的时间和资源。配备摄像头的小型无人机（UAV）有可能加快搜索过程，使搜索人员能够查看感兴趣区域的空中视频，同时与附近的地面搜索人员密切协调。在本文中，我们报告的经验教训，试图使用无人机支持WiSAR。我们的研究方法在很大程度上依赖于实地试验，这些试验涉及在执业搜索和救援人员的指导下进行的搜索，但使用的是模拟失踪人员。这些实地试验的经验教训包括在视频中看到事物的直接重要性，现场需要定义和支持搜索团队中的各种角色，角色特定的需求，如通过提供可视化工具来支持系统搜索以代表搜索的质量，以及持续需要更好地支持地面和视频搜索人员之间的互动。令我们惊讶的是，复杂的自主搜索模式并没有我们预期的那么重要，尽管视频增强和可视化搜索进度的进步，以及正在进行的失踪人员可能位置建模工作，为无人机路径规划，搜索质量和移动失踪人员的可能位置之间的闭环开辟了可能性。
Wilderness Search and Rescue (WiSAR) is the process of finding and assisting persons who are lost in remote wilderness areas. Because such areas are often rugged or relatively inaccessible, searching for missing persons can take huge amounts of time and resources. Camera-equipped mini-Unmanned Aerial Vehicles (UAVs) have the potential for speeding up the search process by enabling searchers to view aerial video of an area of interest while closely coordinating with nearby ground searchers. In this paper, we report on lessons learned by trying to use UAVs to support WiSAR. Our research methodology has relied heavily on field trials involving searches conducted under the direction of practicing search and rescue personnel but using simulated missing persons. Lessons from these field trials include the immediate importance of seeing things well in the video, the field need for defining and supporting various roles in the search team, role-specific needs like supporting systematic search by providing a visualization tool to represent the quality of the search, and the on-going need to better support interactions between ground and video searchers. Surprisingly to us, sophisticated autonomous search patterns were less critical than we anticipated, though advances in video enhancement and visualizing search progress, as well as ongoing work to model the likely location of a missing person, open up the possibility of closing the loop between UAV path-planning, search quality, and the likely location of a moving missing person.