{"type":"ScholarlyArticle","title":"Disturbance-Aware Hybrid Learning for Robust and Adaptive UAV Flight in Extreme Winds","authors":[{"name":"Huidong Liu","slug":"huidong-liu","given":"Huidong","family":"Liu","affiliation":""},{"name":"Jiarui Dou","slug":"jiarui-dou","given":"Jiarui","family":"Dou","affiliation":""},{"name":"Jiangshan Ai","slug":"jiangshan-ai","given":"Jiangshan","family":"Ai","affiliation":""},{"name":"Enwen Hu","slug":"enwen-hu","given":"Enwen","family":"Hu","affiliation":""},{"name":"Xianlei Long","slug":"xianlei-long","given":"Xianlei","family":"Long","affiliation":""},{"name":"Mingyan Li","slug":"mingyan-li","given":"Mingyan","family":"Li","affiliation":""},{"name":"Chao Chen","slug":"chao-chen","given":"Chao","family":"Chen","affiliation":""},{"name":"Fuqiang Gu","slug":"fuqiang-gu","given":"Fuqiang","family":"Gu","affiliation":""}],"abstract":"Safe and precise maneuvering of quadrotor unmanned aerial vehicles (UAVs) in high-speed wind environments remains a critical challenge. Wind disturbances are nonlinear, time-varying, and difficult to model, causing traditional controllers to struggle with perception and compensation, especially under unseen wind distributions. To address these limitations, we introduce WA-TD3, a data-driven control framework that enables real-time wind disturbance perception and adaptive compensation without dedicated wind sensors. WA-TD3 employs a deep residual network to extract wind characteristics from temporal patterns in state deviations, forming a dynamics residual-driven perception mechanism that implicitly models and compensates for unknown winds. This residual is integrated into a perception-augmented reinforcement learning architecture, providing the policy with enhanced state information for proactive disturbance-aware control. Extensive experiments on complex trajectories under varying wind intensities demonstrate that WA-TD3 consistently outperforms state-of-the-art methods, achieving over 62% improvement in tracking accuracy under strong winds.","doi":"10.24963/ijcai.2026/844","url":"https://ijcai.org/proceedings/2026/844","pdf":"https://ijcai.org/proceedings/2026/0844.pdf","markdown":"https://ijcai.org/proceedings/2026/844.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/844","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"AI and Robotics","track":"AI and Robotics","number":844,"pages":{"first":7592,"last":7600},"keywords":["AIR: Robot control, planning, and execution with guarantees","Robot control, planning, and execution with guarantees: Safe and robust control under uncertainty","Safety, trustworthiness, generalizability, and evaluation: Theoretical and algorithmic guarantees on safety, robustness, and out-of-distribution generalization"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}