{"ID":2846960,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.00814","arxiv_id":"2511.00814","title":"Real-Time Learning of Predictive Dynamic Obstacle Models for Robotic Motion Planning","abstract":"Autonomous systems often must predict the motions of nearby agents from partial and noisy data. This paper asks and answers the question: \"can we learn, in real-time, a nonlinear predictive model of another agent's motions?\" Our online framework denoises and forecasts such dynamics using a modified sliding-window Hankel Dynamic Mode Decomposition (Hankel-DMD). Partial noisy measurements are embedded into a Hankel matrix, while an associated Page matrix enables singular-value hard thresholding (SVHT) to estimate the effective rank. A Cadzow projection enforces structured low-rank consistency, yielding a denoised trajectory and local noise variance estimates. From this representation, a time-varying Hankel-DMD lifted linear predictor is constructed for multi-step forecasts. The residual analysis provides variance-tracking signals that can support downstream estimators and risk-aware planning. We validate the approach in simulation under Gaussian and heavy-tailed noise, and experimentally on a dynamic crane testbed. Results show that the method achieves stable variance-aware denoising and short-horizon prediction suitable for integration into real-time control frameworks.","short_abstract":"Autonomous systems often must predict the motions of nearby agents from partial and noisy data. This paper asks and answers the question: \"can we learn, in real-time, a nonlinear predictive model of another agent's motions?\" Our online framework denoises and forecasts such dynamics using a modified sliding-window Hanke...","url_abs":"https://arxiv.org/abs/2511.00814","url_pdf":"https://arxiv.org/pdf/2511.00814v2","authors":"[\"Stella Kombo\",\"Masih Haseli\",\"Skylar X. Wei\",\"Joel W. Burdick\"]","published":"2025-11-02T05:54:30Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.LG\",\"eess.SY\"]","methods":"[]","has_code":false}