Mid-air collisions with drones: Assessment of collision scenarios and of drone operation risks in urban areas

Recent technological developments have led to the emergence of affordable and increasingly capable remotely-piloted aircraft or ‘drones’. Aside opportunities, this also presents a potential threat to the safety of crewed aviation. This paper discusses ongoing work to evaluate and mitigate the risk and threats associated with mid-air collisions as part of initiatives to maintain and improve the high standards of aviation safety in a rapidly evolving environment. The work reported includes activities in support of two research initiatives. The first is an ongoing ‘Horizon 2020’-funded project of the European Union Aviation Safety Agency (EASA) and carried out by QinetiQ in the UK, which aims to deepen the understanding of the effects of a potential mid-air collision and identify drone design strategies to mitigate their severity. The second is research at TUD that uses statistical airspeed data distributions assessed in QinetiQ’s project to estimate aircraft collision risks. The risk model, which is not endorsed by EASA or QinetiQ, uses stochastically acting vehicles and pilots in an agent-based simulation, now tailored to regions where commercial drones may operate in the vicinity of airports or existing and emerging urban air operations. Work in support of QinetiQ’s programme includes novel fusion and processing of large datasets (including ADS-B histories) to derive probabilistic models of potential collision speeds for different classes of aircraft; this will inform ongoing detailed collision simulation and testing studies. Work at TUD estimates probabilities for an urban scenario using that data; results indicate that management of risks within acceptable limits is possible. TUD conclude that appropriate vertical/lateral separation to manned aviation is required for UAS operations to keep collision risks acceptable. Integration of this type of agent simulation as ‘air risk’ assessment in SORA is proposed.