CAREER: Toward Autonomous Decision Making and Coordination in Intelligent Unmanned Aerial Vehicles' Operation in Dynamic Uncertain Remote Areas

无人机（uav）已经越来越多地用于一些商业和民用应用，如包裹递送、交通监控、精准农业、遥感、边境巡逻、危害监测、救灾和搜索和救援行动，为附近的地面指挥站收集数据/图像。当前基于无人机的操作的实现严重依赖于人类控制器的控制、推理、任务分配和规划，这可能会限制无人机在任务中的操作，因为在任务之前，人类控制器无法完全观察到操作场，并且在任务期间，无人机与地面站之间或队友无人机之间无法获得可靠和连续的通信。无人机可以在这种非结构化和未知环境中特别有用，以提供敏捷的测量或搜索和救援行动。因此，无人机技术的未来发展重点是开发小型、低成本、具有更高自主水平的智能无人机。这种无人机可以以最少的人为干预和更低的成本，促进由合作无人机编队执行的各种复杂任务。本研究的目的是在动态和未知环境中，以最少的人为干预，为完全自主的多智能体系统（如无人机）网络的操作、态势感知、协调和通信开发理论和实践框架。该研究为远程和动态环境下的自主多智能体系统提供了一套新的应用。该项目涉及一套集成的研究、实施和实验验证推进，以开发无人机系统中自主决策、联盟形成、协调、频谱管理和任务分配的新框架。所开发的技术可用于其他多智能体认知系统，如机器人系统和自动驾驶车辆，这些系统需要在有限的人为干预下进行快速搜索、监视和反应。该项目还提供了一系列教育和推广活动，将研究成果整合到课程改进、学生指导、吸引代表性不足的少数民族和女学生、为中小学生开发基于无人机的动手传感实验，以及通过与Flagstaff科学节合作，向社区推广以提高公众对无人机系统新应用的认识。该奖项反映了美国国家科学基金会的法定使命，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。

Unmanned aerial vehicles (UAVs) have been increasingly utilized in several commercial and civil applications such as package delivery, traffic monitoring, precision agriculture, remote sensing, border patrol, hazard monitoring, disaster relief, and search and rescue operations to collect data/imagery for a ground command station nearby. Current implementations of UAV-based operations heavily rely on control, inference, task allocation, and planning from a human controller that can limit the operation of drones in missions where the operation field is not fully observable to the human controller prior to the mission and reliable and continuous communication is not available between the UAVs and the ground station or among the teammate UAVs during the mission. The UAVs can be particularly useful in such unstructured and unknown environments to provide agile surveying or search-and-rescue operations. Therefore, the future of UAV technology focuses on the development of small, low-cost, and smart drones with a higher level of autonomy. Such drones can facilitate a wide range of sophisticated missions performed by a fleet of cooperative UAVs with minimum human intervention and lower cost. The objective of this research is to develop theoretical and practical frameworks for operation, situational awareness, coordination, and communication of a network of fully autonomous multi-agent systems (e.g., UAVs) in dynamic and unknown environments with minimum human interventions. This research can facilitate a new set of applications for autonomous multi-agent systems in remote and dynamic environments. This project involves an integrated set of research, implementation, and experimental validation thrusts to develop novel frameworks for autonomous decision making, coalition formation, coordination, spectrum management, and task allocation in UAV systems. The developed techniques can be utilized in other multi-agent cognitive systems such as robotic systems, and autonomous driving vehicles where quick search, surveillance, and reactions are required with limited human interventions.This project also offers a number of educational and outreach activities to integrate the results of this research in curriculum enhancement, student mentorship, engaging underrepresented minority and female students, developing hands-on UAV-based sensing experiments for elementary and middle school students and outreach to the community to enhance public awareness about new applications of UAV systems through collaboration with Flagstaff Festival of Science.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.