MRI: Development of a Solar UAV Instrument

MRI：太阳能无人机仪器的开发

• 批准号: 1531330
• 负责人: Nikolaos Papanikolopoulos
• 金额: $ 152.55万
• 依托单位: University of Minnesota-Twin Cities
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2015
• 资助国家: 美国
• 起止时间: 2015-10-01 至 2025-03-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1531330&HistoricalAwards=false
• 关键词: MRI; Development; Solar; UAV; Instrument

This project, developing a high efficiency solar power enabled aerial instrument that incorporates sensory and processing requirements into the design methodology, focuses on the development of a (robotic) instrument that fills a niche in certain applications (i.e., small scale solar powered Unmanned Aerial Vehicles (UAVs)). The work involves the creation of a platform for real-world information gathering applications with special focus on robust navigation, distributed sensing, and collaborative scenarios. In particular, the development of a small scale solar powered UAV provides a robotic platform capable of communication, sensory coverage, and flight endurance unattainable through traditional UAV design. Existing UAVs utilizing solar power are constrained to large aircraft designs requiring a traditional runway for takeoff and landing. In contrast, electric powered small scale UAVs suffer from minimal flight time. Additionally, aerial robots provide significant advantages over ground based systems as they are unaffected by terrain and obstacles, and provide an information-rich vantage point from the air. Conventional aerial robots are significantly limited by their flight time and therefore their deployment is severely restricted. Flight time has been the central limitation for airborne sensory information and has prevented experimental research and real-world applications from being performed. The development of a high efficiency aircraft that leverages solar energy as a resource provides a solution to the flight time problem.The methodologies mentioned involve the incorporation of hierarchical planning methods that include high-level reasoning for the optimal number of UAVs/sensors required, and low-level reasoning for efficient sensor placement throughout the environment. Specifically, the use of solar powered UAV platforms will enable work in the areas of precision agriculture and environmental science, requiring strong demand for high endurance systems capable of supporting a variety of sensor and measurement units. (For example, timely and repetitive relevant information regarding crop health is necessary for corrective actions to be implemented.) Additionally, collaborative operation of dynamically placed sensor platforms and devices can only be enabled through the use of small solar powered airplanes like the ones to be implemented. The instrument that this project funds enables work in application areas that require continuous and repetitive operation such as Energy, Environment, Agriculture, etc. Consequently, this work addresses the- Development of a small scale solar powered platform that is capable of multi-day flight, - Experimental validation of the scaled down solar UAV instrument, - Long-term solar powered flight planning based on sensory data collected, and- Creation of benchmarks that will allow comprehensive evaluation of the small solar powered UAV instrument.

该项目开发一种高效率的太阳能航空仪器，将传感和处理要求纳入设计方法，重点是开发一种(机器人)仪器，填补某些应用(即小型太阳能无人机)的利基市场。这项工作涉及为现实世界的信息收集应用程序创建一个平台，特别关注健壮的导航、分布式传感和协作场景。特别是，小型太阳能无人机的开发提供了一个机器人平台，能够进行通信、感知覆盖和飞行耐力，这是传统无人机设计无法达到的。现有的利用太阳能的无人机仅限于需要传统跑道起飞和降落的大型飞机设计。相比之下，电动小型无人机的飞行时间最短。此外，空中机器人与地面系统相比具有显著的优势，因为它们不受地形和障碍物的影响，并且从空中提供了一个信息丰富的有利位置。传统的空中机器人在很大程度上受到飞行时间的限制，因此它们的部署受到严重限制。飞行时间一直是空中感知信息的中心限制，并阻碍了实验研究和现实世界的应用。利用太阳能作为一种资源的高效率飞机的开发为飞行时间问题提供了一个解决方案。所提到的方法包括纳入分层规划方法，包括对所需的无人机/传感器的最佳数量进行高层推理，以及对整个环境中有效的传感器放置进行低层推理。具体地说，太阳能无人机平台的使用将使精准农业和环境科学领域的工作成为可能，这需要能够支持各种传感器和测量单元的高耐久性系统的强劲需求。(例如，有关作物健康的及时和重复的相关信息是实施纠正行动所必需的。)此外，动态放置的传感器平台和设备的协作操作只能通过使用像将要实施的小型太阳能飞机来实现。该项目资助的仪器有助于在能源、环境、农业等需要连续和重复操作的应用领域开展工作。因此，这项工作致力于-开发一个能够进行多天飞行的小型太阳能供电平台，-对缩小规模的太阳能无人机仪器进行实验验证，-根据收集的传感数据制定长期太阳能供电飞行计划，以及-创建基准，以便能够对小型太阳能无人机仪器进行全面评估。

项目成果

Robotic Embodiment of Human-Like Motor Skills via Reinforcement Learning

通过强化学习实现类人运动技能的机器人

• DOI: 10.1109/lra.2022.3147453
• 发表时间: 2022
• 期刊: IEEE Robotics and Automation Letters
• 影响因子: 5.2
• 作者: Guzman, Luis;Morellas, Vassilios;Papanikolopoulos, Nikolaos
• 通讯作者: Papanikolopoulos, Nikolaos