Learning2Fly

学习飞翔

• 批准号: 2895338
• 金额: --
• 依托单位: University of Surrey
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2023
• 资助国家: 英国
• 起止时间: 2023 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2895338
• 关键词: Learning2Fly

Despite recent advances in sensing, actuation and computation, robots cannot come close to matching the agility of natural Lyers. Newborn birds and bats outstrip even the most advanced robots within only a few attempts at Light. How does life learn to move in the unsteadiness and chaos that characterise outdoor Light? How does body shape and structure interact with cognition and learning? The project will combine cutting edge robotic Light experiments with numerical simulations and machine learning techniques to investigate the ways in which Lying techniques are learned. Ideally, these experiments will be matched with observations of bird Light using photogrammetry to measure the aerodynamics of live animals. Ultimately, the knowledge generated will feed into new approaches to the design of unmanned aircraft which allow robust and adaptable Light and open new opportunities to deploy aerial robots in the modern world. Insight into the learning process will also help train future pilots. The PhD research activity will include the development of biomimetic wings, to be used with an existing Light experiment, using a robotic catapult to produce large volumes of Light data in an indoor Light arena. The design of the robotic experiment will be informed by the observation of live bird Light. The resulting data will be used to support advanced numerical modelling to be able to predict and control Light. The numerical modelling approach will be driven by machine-learning techniques and artiVcial intelligence, which will have been trained for increasingly complex situations. The student will be a member of the Centre Aerodynamics & Environmental Flow Research in the Department of Mechanical Engineering Sciences (MES) at the University of Surrey. Work on machine learning will be carried out in collaboration with the School of Psychology at the University of Surrey. The members of the research team have an excellent collaboration network with leading research groups in the UK and internationally

尽管最近的感测，驱动和计算取得了进步，但机器人仍无法接近与天然莱斯的敏捷性相匹配。新生的鸟类和蝙蝠甚至超过了最先进的机器人，只有几次尝试。生活如何学习在室外光中特征的不稳定和混乱中移动？身体形状和结构如何与认知和学习相互作用？该项目将将最先进的机器人光实验与数值模拟和机器学习技术相结合，以研究学习说谎技术的方式。理想情况下，这些实验将与使用摄影测量法测量活动物的空气动力学的鸟类光观察相匹配。最终，所产生的知识将以新的无人飞机设计为新的方法，这些飞机允许强大而适应能力的光线和开放新的机会在现代世界中部署空中机器人。洞悉学习过程还将有助于培训未来的飞行员。博士研究活动将包括仿生机翼的发展，将与现有的光实验一起使用，使用机器人弹射器在室内光竞技场中产生大量的光数据。机器人实验的设计将通过观察活鸟的光线来告知。所得数据将用于支持高级数值建模，以预测和控制光。数值建模方法将由机器学习技术和Artivcial Intelligence驱动，该技术将接受越来越复杂的情况进行培训。该学生将是萨里大学机械工程科学系（MES）中心空气动力和环境流研究的成员。机器学习的工作将与萨里大学心理学学院合作进行。研究小组的成员与英国领先的研究小组和国际领先的研究小组建立了一个很好的合作网络