Autors: Puliyski, A. V., Serbezov, V. S.
Title: AI-Based Assistant for SORA: Approach, Interaction Logic, and Perspectives for Cybersecurity Integration †
Keywords: AI assistant, context-aware dialogue, drones, operational safety, regulatory compliance, SORA, UAS

Abstract: This article presents the design, development, and evaluation of an AI-based assistant tailored to support users in the application of the Specific Operations Risk Assessment (SORA) methodology for unmanned aircraft systems. Built on a customized language model, the assistant was trained using system-level instructions with the goal of translating complex regulatory concepts into clear and actionable guidance. The approach combines structured definitions, contextualized examples, constrained response behavior, and references to authoritative sources such as JARUS and EASA. Rather than substituting expert or regulatory roles, the assistant provides process-oriented support, helping users understand and complete the various stages of risk assessment. The model’s effectiveness is illustrated through practical interaction scenarios, demonstrating its value across educational, operational, and advisory use cases, and its potential to contribute to the digital transformation of safety and compliance processes in the drone ecosystem.

References

  1. Andrysiak J. Fraczek S. Risks of Drone Use in Light of Literature Studies Sensors 2024 24 1205 Available online: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10892979 (accessed on 13 February 2025) 10.3390/s24041205 38400363
  2. JARUS Guidelines on Specific Operations Risk Assessment (SORA) 2017 Available online: https://jarus-rpas.org (accessed on 10 February 2025)
  3. EASA Easy Access Rules for Unmanned Aircraft Systems European Union Aviation Safety Agency Brussels, Belgium 2024
  4. Martinez C. Sanchez-Cuevas P.J. Gerasimou S. Bera A. SORA Methodology for Multi-UAS Airframe Inspections in an Airport Drones 2021 5 141 Available online: https://www.mdpi.com/2504-446X/5/4/141 (accessed on 15 January 2025) 10.3390/drones5040141
  5. Schnüriger P. Schreiber J. Widmer K. Lenhart P.M. SORA Tool—A Specific Operation Risk Assessment Tool for Civilian Drone Operations Drones 2025 9 1 11 10.1139/dsa-2024-0060
  6. Jeelani I. Gheisari M. Safety Challenges of UAV Integration in Construction Saf. Sci. 2021 144 105473 Available online: https://www.sciencedirect.com/science/article/pii/S0925753521003167 (accessed on 12 February 2025) 10.1016/j.ssci.2021.105473
  7. Tran T.D. Cybersecurity Risk Assessment for Unmanned Aircraft Systems Ph.D. Thesis Université Grenoble Alpes Saint-Martin-d’Hères, France 2021 Available online: https://hal.science/tel-03200719v1 (accessed on 4 February 2025)
  8. Available online: http://jarus-rpas.org/publications/ (accessed on 19 January 2025)
  9. Available online: https://www.eurocontrol.int/ (accessed on 22 February 2025)
  10. Wyszywacz W. SORA: Assumptions and Evaluation of the Method Rev. Eur. De Derecho De La Naveg. Marítima Y Aeronáutica 2023 39 25 45
  11. Denney E. Pai G. Tool Support for Assurance Case Development Autom. Softw. Eng. 2018 25 435 499 10.1007/s10515-017-0230-5
  12. Pinto G. De Souza C. Rocha T. Steinmacher I. Souza A. Monteiro E. Developer Experiences with a Contextualized AI Coding Assistant arXiv 2023 2311.18452
  13. Nogueira A. Silva J. Reis A. Unmanned Aircraft Systems: A Pathway to Obtain a Design Verification Report J. Airl. Airpt. Manag. 2024 14 19 37 Available online: https://www.jairm.org/index.php/jairm/article/viewFile/421/160 (accessed on 9 February 2025) 10.3926/jairm.421
  14. Denney E. Pai G. Whiteside I. Modeling the Safety Architecture of UAS Flight Operations Proceedings of the Computer Safety, Reliability, and Security (SAFECOMP 2017), LNCS 10488 Trento, Italy 13–15 September 2017 Springer Berlin/Heidelberg, Germany 2017 162 178 10.1007/978-3-319-66284-8_14
  15. Denney E. Pai G. Whiteside I. Model-Driven Development of Safety Architectures Proceedings of the 2017 ACM/IEEE 20th International Conference on Model Driven Engineering Languages and Systems (MODELS) Austin, TX, USA 17–22 September 2017 156 166 10.1109/MODELS.2017.17
  16. Maharaj A.V. Qian K. Bhattacharya U. Fang S. Galatanu H. Garg M. Hanessian R. Kapoor N. Russell K. Vaithyanathan S. et al. Evaluation and Continual Improvement for an Enterprise AI Assistant arXiv 2024 2407.12003
  17. Castro D.G. García E.V. Safety Challenges for Integrating U-Space in Urban Environments Proceedings of the IEEE International Conference on Unmanned Aircraft Systems (ICUAS) Athens, Greece 15–18 June 2021 Available online: https://ieeexplore.ieee.org/document/9476883 (accessed on 15 January 2025)
  18. Del Guercio A.M. Development of a WebApp for Safe Mission Planning for UAS in Urban Areas Master’s Thesis Politecnico di Torino Turin, Italy 2024 Available online: https://webthesis.biblio.polito.it/secure/33138/1/tesi.pdf (accessed on 24 February 2025)
  19. Rana M. Saboor K. Vishal S. Hussain A. AI-Enabled Intelligent Assistant for Personalized and Adaptive Learning in Higher Education arXiv 2023 2309.10892
  20. Available online: http://jarus-rpas.org/wp-content/uploads/2024/06/SORA-v2.5-Cyber-Extension-Release-JAR_doc_31.pdf (accessed on 23 January 2025)
  21. Tran T.D. Thiriet J.M. Marchand N. El Mrabti A. A Cybersecurity Risk Framework for Unmanned Aircraft Systems under Specific Category J. Intell. Robot. Syst. 2022 104 4 Available online: https://link.springer.com/article/10.1007/s10846-021-01512-0 (accessed on 16 January 2025) 10.1007/s10846-021-01512-0
  22. Barber D. Bayesian Reasoning and Machine Learning Cambridge University Press Cambridge, UK 2012

Issue

Engineering Proceedings, vol. 100, 2025, Bulgaria, https://doi.org/10.3390/engproc2025100065

Вид: статия в списание, публикация в реферирано издание, индексирана в Scopus