Agentic AI for Safety-critical Multi-drone Systems: Challenges and Opportunities

Abstract

Multi-drone systems are increasingly positioned for safety-critical missions such as search and rescue (SAR) and critical infrastructure monitoring. Yet, real-world adoption remains constrained not only by autonomy performance, but by the difficulty of integrating agentic behavior into professional work: operators must understand, trust, and govern automation under uncertainty, time pressure, and accountability. This position paper synthesizes the ambitions and lessons from two ongoing efforts:

Categories

@misc{merritt2026agentic,
  title = {{Agentic AI for Safety-critical Multi-drone Systems: Challenges and Opportunities}},
  author = {Timothy Merritt and Alejandro Jarabo-Peñas and Juan Bravo-Arrabal and Maria-Theresa Bahodi and Anders Lyhne Christensen},
  year = {2026},
  month = aug,
  eprint = {2608.21444},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.21444}
}