CPS: Medium: Collaborative Research: Virtual Sully: Autopilot with Multilevel Adaptation for Handling Large Uncertainties

在正常运行期间，飞机是由自动驾驶仪操纵的。当自动驾驶仪感觉到飞行包线附近或之外的危险情况时，自动驾驶仪会自动脱离接触，将控制权归还给飞行员。训练有素的飞行员通常可以应对适度的、超出范围的挑战。2009年，全美航空1549航班上，机长切斯利·苏伦伯格和副驾驶杰弗里·斯基尔斯在乔治·华盛顿大桥东北方向撞上了一群鹅，在曼哈顿上空突然失去了所有引擎动力，能够处理严重受损飞行包线的飞行员是非常了不起的。飞行员非常熟练地将飞机滑行到曼哈顿中城附近的哈德逊河上，救了所有乘客，并避免了纽约市的一场灾难性坠机。美国国家运输安全委员会的官员称，这是航空史上最成功的一次降落。这种在异常情况下仍能安全运行的能力是这个项目--虚拟沙利的本质。虚拟沙利技术是朝着完全无人驾驶自主的方向发展的，能够识别故障/故障，估计剩余的控制权，评估环境，规划新的可行任务，在受损的飞行包线内进行路径规划并安全执行。该体系结构取代了传统的自顶向下的任务规划、轨迹生成、跟踪稳定控制器之间的单向自适应，而是任务规划、轨迹生成和控制器参数自适应之间的双向自适应，提高了控制系统的稳定性和鲁棒性。主要包括：1)监控和能力审计；2)多层自适应的高保证控制；3)具有实时保证的无人自主系统的容错体系结构；4)开发半实物仿真环境和使用无人机原型进行飞行试验。能够承受高压力情况的容错计算基础设施将集成在适应多个级别的飞行控制体系结构中。对无人机剩余能力内的任务和再生轨迹的可行性评估是在实时保证下进行的。该试验台基于对各种故障的硬件在环模拟，以及使用真实无人机的广泛测试。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

During normal operations an aircraft is operated by its autopilot. When the autopilot sense a dangerous condition, near or outside of the flight envelope, the autopilot disengages itself, returning control to the pilot. Well-trained pilots typically can deal with modest out-of-envelope challenges. A pilot who can deal with a significantly compromised flight envelope is very remarkable as happened with Captain Chesley Sullenberger ("Sully") and co-pilot Jeffrey Skiles on US Airways Flight 1549 in 2009 when the aircraft struck a flock of geese just northeast of the George Washington Bridge and suddenly lost all engine power over Manhattan. The pilots glided their plane extraordinarily skillfully to a ditching in the Hudson River off Midtown Manhattan, saving all the passengers and averting a catastrophic crash in New York City. The National Transportation Safety Board official described it as the most successful ditching in aviation history. This capability to operate safely despite the exceptional situation well-outside the norm is the essence of this project, Virtual Sully.Virtual Sully technology is a development towards full pilotless autonomy, capable of identifying the failure/fault, estimating the remaining control authority, assessing the environment and planning a new feasible mission, doing path planning and executing it safely within the compromised flight envelope. This architecture replaces the traditional top-down one-way adaptation between mission planning, trajectory generation, tracking and stabilizing controller, with a two-way adaptation between mission planning, trajectory generation, and the adaptation of controller parameters to improve the stability and robustness of the control system. The following thrusts are considered: 1) monitoring and capability auditing; 2) high-assurance control with multi-level adaptation; 3) fault-tolerant architecture for unmanned autonomous systems (UAS) with real-time guarantees; 4) development of hardware-in-the loop simulation environment and flight tests using unmanned air vehicle (UAV) prototypes. Fault-tolerant computing infrastructure that can withstand high-stress situations will be integrated within flight control architecture that adapts at multiple levels. The feasibility evaluation of the missions and regenerated trajectories within UAV's remaining capabilities is pursued with real-time guarantees. The testbed is based on hardware-in-the-loop simulation for various failures, as well as extensive tests using real UAVs.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.