{"ID":6029833,"CreatedAt":"2026-07-08T02:57:47.77373338Z","UpdatedAt":"2026-07-10T17:41:27.792927618Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.06535","arxiv_id":"2607.06535","title":"Neural-ESO: A Dual-Pathway Architecture for Provably Robust Learning-Based Control","abstract":"A learning-enabled disturbance-rejection framework based on a Neural Extended State Observer (Neural-ESO) is presented in this letter. Unlike existing learning-based control methods that largely rely on the learned model once deployed, Neural-ESO adopts a dual-pathway architecture: a predictive pathway uses a neural network to provide a feedforward disturbance estimate that accelerates convergence, while a corrective pathway employs a conventional ESO to compensate prediction errors and prevent over-reliance on the neural component. Using Lyapunov theory and a small-gain analysis, we show that enforcing a Lipschitz bound on the learning component guarantees uniform ultimate boundedness of the closed-loop error dynamics. The proposed framework is validated on a quadrotor landing task subject to strong ground-effect disturbances across normal and out-of-distribution scenarios, demonstrating accuracy-robustness trade-off and greater operational reliability during training, deployment, and transfer compared with state-of-the-art baselines.","short_abstract":"A learning-enabled disturbance-rejection framework based on a Neural Extended State Observer (Neural-ESO) is presented in this letter. Unlike existing learning-based control methods that largely rely on the learned model once deployed, Neural-ESO adopts a dual-pathway architecture: a predictive pathway uses a neural ne...","url_abs":"https://arxiv.org/abs/2607.06535","url_pdf":"https://arxiv.org/pdf/2607.06535v1","authors":"[\"Fan Zhang\",\"Richie Suganda\",\"Jinfeng Chen\",\"Wenhua Liu\",\"Hantao Fu\",\"Bin Hu\",\"Qin Lin\"]","published":"2026-07-07T17:41:38Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"eess.SY\"]","methods":"[]","has_code":false}