Unmanned aircraft systems (UAS) have experienced tremendous growth through both commercial (i.e., toys and videography) and defense avenues. The rapid expansion, particularly in the consumer market, has outpaced regulatory bodies. Certification to commercially operate such vehicles currently requires the successful completion of a knowledge examination, without the need to physically operate a vehicle. The focus of the work presented herein is on quantifying the pilot and multi-rotor performance in an attempt to provide quantitative metrics that can be used to establish training and certification for pilots and aircraft. Test pilots were categorized based on their experience level, and the quadrotor unmanned aircraft was categorized based on the flight control mode. Cross-track command (CTC) and path error (PE) were calculated as potential time-domain metrics to quantify pilot and quadcopter performance. Individual binary logistic regression models were developed to identify the pilot experience level (PEL) and UAV control level (UCL) from the decision tree outcomes. A verification test case was included to evaluate the established regression models. Results show that the models can evaluate pilot and quadcopter performance individually, which can be used to develop the pilot training curriculum and/or evaluate pilot effectiveness in specific flight scenarios.

无人飞机系统（UAS）通过商业（即玩具和录像）和防御途径都经历了巨大的增长。快速的增长，特别是在消费市场，已经超过了监管机构。目前，要对此类车辆进行商业操作进行认证，就需要成功完成知识考试，而无需实际操作车辆。本文介绍的工作重点是量化飞行员和多旋翼的性能，以尝试提供可用于为飞行员和飞机建立培训和发证的定量指标。根据他们的经验水平对测试飞行员进行分类，并根据飞行控制模式对四旋翼无人飞机进行分类。计算出跨轨命令（CTC）和路径误差（PE）作为潜在的时域指标，以量化飞行员和四旋翼飞机的性能。开发了单独的二进制逻辑回归模型，以从决策树结果中识别飞行员经验水平（PEL）和无人机控制水平（UCL）。包括一个验证测试用例，以评估已建立的回归模型。结果表明，该模型可以分别评估飞行员和四旋翼飞机的性能，可用于制定飞行员培训课程和/或评估飞行员在特定飞行场景下的效能。包括一个验证测试用例，以评估已建立的回归模型。结果表明，该模型可以分别评估飞行员和四旋翼飞机的性能，可用于制定飞行员培训课程和/或评估飞行员在特定飞行场景下的效能。包括一个验证测试用例，以评估已建立的回归模型。结果表明，该模型可以分别评估飞行员和四旋翼飞机的性能，可用于制定飞行员培训课程和/或评估飞行员在特定飞行场景下的效能。