摘要: We present a hybrid pointing-correction framework for robotic telescopes and evaluate it under strict temporal generalization using real Alt-Az guiding data from a 1 m telescope in the Las Cumbres Observatory network. The framework combines a 19-parameter rack model as a physically motivated analytic backbone with an XGBoost-based residual regressor that learns the remaining error from rack-term contributions, Alt-Az geometry, and a compact set of environmental features. The primary evaluation uses rolling temporal splits, so that each test segment is strictly later than the data used for training and model selection, with a hybrid strategy achieving the best overall future-window pointing accuracy among the tested model families. This shows a clear advantage over the purely analytic and purely data-driven baselines, while the improvement over a simpler residual-learning baseline is more modest. In terms of weighted mean vector root-mean-square residual (VecRMS) the corresponding values are 12.75″ for Hybrid, 14.95″ for Rack+ResTree, 18.14″ for Rack-only, and 21.87″ for Pure Machine Learning (PureML). Additional drift diagnostics provide descriptive evidence of a temporal distribution shift over the studied interval, supporting the use of time-aware evaluation. A strictly causal offline replay also suggests that a conservative validation-gated model-refresh policy may improve future-window pointing accuracy under controlled conditions. Additional analyses of condition-wise robustness, feature relevance, and computational overhead support the practical feasibility of the framework.