An Intelligent Autopilot System that learns piloting skills from human pilots by imitation

Abstract

An Intelligent Autopilot System (IAS) that can learn piloting skills by observing and imitating expert human pilots is proposed. IAS is a potential solution to the current problem of Automatic Flight Control Systems of being unable to handle flight uncertainties, and the need to construct control models manually. A robust Learning by Imitation approach is proposed which uses human pilots to demonstrate the task to be learned in a flight simulator while training datasets are captured from these demonstrations. The datasets are then used by Artificial Neural Networks to generate control models automatically. The control models imitate the skills of the human pilot when performing piloting tasks including handling flight uncertainties such as severe weather conditions. Experiments show that IAS performs learned take-off, climb, and slow ascent tasks with high accuracy even after being presented with limited examples, as measured by Mean Absolute Error and Mean Absolute Deviation. The results demonstrate that the IAS is capable of imitating low-level sub-cognitive skills such as rapid and continuous stabilization attempts in stormy weather conditions, and high-level strategic skills such as the sequence of sub-tasks necessary to pilot an aircraft starting from the stationary position on the runway, and ending with a steady cruise.