Search

Adaptive and Learning Agents (ALAs) bring computational intelligence to their Cyber Physical host systems to adapt to novel situations encountered in their complex operational environment. They do so by learning from their experience to improve their performance. RTCA DO-178C specifies a stringent certification process for airborne software which represents several challenges when applied to an ALA in regards of functional completeness, functional correctness, testability and adaptability. This research claims that it is possible to certify an Adaptive Learning Unmanned Aerial Vehicle (UAV) Agent designed as per a Cognitive Architecture with current DO-178C certification process when leveraging a qualified tool (DO-330), Model-Based Development and Verification (DO-331) and Formal Methods (DO-333). The research consists in developing, as a case study, an ALA embedded in a UAV aimed at neutralizing rogue UAVs in the vicinity of civil airports and test it in the field. This article is the plan to complete, by end 2022, a dissertation currently in its confirmation phase.

Purpose: This research studies the UAV incidents in the vicinity of worldwide airports in order to deliver a quantitative and qualitative analysis of this phaenomenon, to analyse the risks associated to this threat and propose mitigation measures that brings this risk to an ‘acceptable’ level.Methodology: A population of 139 ‘serious UAV incidents in the vicinity of worldwide airports’ has been constituted on the basis of the FAA and NASA databases and articles published on the Web by online media. This phaenomenon has then been analysed quantitatively using descriptive statistics techniques and qualitatively by analysing in-depth some representative incidents. A risk analysis has then been performed based on the FAA Safety Risk Management 5-steps process to identify the hazards i.e. the root causes of those UAV incidents, determine their outcome i.e. negative consequences that jeopardize airports objectives and assign them a severity level and likelihood i.e. frequency level. Analysed risks have then been assessed based on FAA ARP Risk Matrix. Mitigation measures (prevention, deterrence, denial, detection, neutralisation) have been identified following a ‘Defence-in-Depth’ approach.Findings: The findings of the study are that those UAV incidents are more numerous than anticipated and happen higher and further from the airports than expected: they happen not only in CTRs but also in TMAs. This has an impact on the mitigation measures that shall not only be deployed at airports side but also be on-boarded in manned aircrafts.Originality: To our knowledge, no study has combined different sources to constitute such a population focused on ‘serious’ UAVs incidents around airports worldwide, has applied the official FAA Safety Risk Management process to assess this risk and followed a structured ‘Defence-in-Depth’ approach typically used in Cybersecurity to mitigate this risk.Keywords: Airport security and safety, Unmanned Aerial Vehicles (UAVs) threat, Risk analysis and mitigation, Counter-UAVs technologies.