A Learning-Based Autonomous Control System Approach for Collision Avoidance within an Unmanned Aircraft

The growing public interest for Unmanned Aircraft Systems (UAS) applications has stimulated the debate over the integration of this kind of aircraft into the civil aviation system. However, the concept of not having a human pilot inside the aircraft presents uncertainties that may impede the creation of proper regulation. Having safety as the main concern for civil aviation, one important principle of aviation to be addressed in an UAS is collision avoidance, a traditionally pilot-dependent functionality. In this regard, as a possible substitute for the pilot in the aircraft, we propose a method for implementing a learning-based autonomous control system focused in guaranteeing collision avoidance. Regarding that safety aspect, we expect such system to be able to compensate for the lack of a human pilot in the aircraft. The proposed approach utilizes the concept of 'Learning from Demonstration' in order to define a behaviour for the autonomous aircraft based on manoeuvres commanded by a human. Therefore, the proposed approach would represent a possible implementation of an autonomous unmanned aircraft that presents the same collision avoidance capabilities observed in (human-based) civil aviation. Additionally, we identify metrics that can be used to select a suitable learning-based method and to compare its performance to those observed in manned aircraft.