Newest papers

Interruption-Aware Recurrent Reinforcement Learning for UAS Navigation Under Temporary Overrides

Christopher Conrad, Deepak Panda, Weisi Guo, Antonios Tsourdos · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28121 · cited by 0 works (OpenAlex) · open-access PDF

Korean

UAS의 안전한 컨텍스트 내부 방해는 전략적 조정이 예방할 수없는 충돌을 해결하기 위해 전술적 탈퇴를 필요로합니다.이 작업은 부분적 관찰력 아래에서 도전적이며, 센서 또는 트래픽 데이터가 실종되거나 지연되거나 악화될 때. 지오메트리 기반 간 방어 방법은 분리 보증을 제공 할 수 있지만 밀접한 충돌에서 제한을 직면합니다. 반복 강화 학습은 반복적으로 배운 정책을 일시적으로 극복하기 위해 제안되었습니다. 이러한 방해가 에이전트가 권한을 회복 할 때 반복적인 정책에 영향을 미치는지 이해하는 연구 격차가 남아 있습니다. 그러나, 운영 방어 방법은 방해 변수를 실행 중 반복적으로 방해 할 수 있음을 보여줍니다

Machine translation (Meta M2M100); the English original follows.

Abstract

Safe autonomous navigation of UASs requires tactical deconfliction to address conflicts that strategic coordination cannot prevent. This task is challenging under partial observability, when sensor or traffic data are missing, delayed, or degraded. Geometry-based methods can offer separation assurances but face limitations in dense encounters. Recurrent reinforcement learning has therefore been proposed to learn navigation policies that integrate observation-action histories to optimise long-term safety-efficiency trade-offs. However, operational safeguards may require a remote pilot, onboard detect-and-avoid system, or runtime assurance mechanism to temporarily override the learned policy. A research gap remains in understanding how these interruptions affect recurrent policies when the agent regains authority. Benchmark evidence shows that interruptions make task variables less decodable from the recurrent hidden state and increase post-interruption collision risk. The findings suggest that altered recurrent context prolongs post-handback degradation through an action-observation feedback loop, in which changed actions alter the flight path and subsequent recurrent updates. To address this vulnerability, we propose three interruption-aware architectures that condition recurrent processing on interruption context through separate feature streams, dedicated interruption memory, or gated environmental features. Across simulations, all three architectures preserve more decodable task information than a standard recurrent policy. Moreover, the strongest architecture reduces post-interruption collisions by 74% and interruption-induced mission failures by 69% relative to the recurrent baseline, without degrading interruption-free performance. These results show that safe interruption does not guarantee safe handback, and support interruption-aware recurrent design for resilient UAS autonomy.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Reinforcement learning, Context (archaeology), Task (project management), Computer science, Collision avoidance, Benchmark (surveying)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange