Pick-to-Learn Calibration of an MPC Policy for an Origin-to-Destination Flight Problem

2026-07-17

AI Summary

This work addresses flight safety under uncertain crosswinds and sparsely connected no-fly zones by proposing a Pick-to-Learn–based model predictive control (MPC) calibration framework. The approach efficiently selects two most informative scenarios from a set of 400 wind-field realizations to calibrate an MPC policy governed by two hyperparameters. By integrating scenario optimization with data compression techniques, the method drastically reduces training data requirements while providing rigorous probabilistic risk guarantees. The learned policy successfully avoids all no-fly zones across the entire test suite and achieves a certified probability risk upper bound of 4.8% with confidence $1 - 10^{-5}$.

Abstract

This paper illustrates the Pick-to-Learn methodology applied to the calibration of a Model Predictive Control policy. While developed around a specific example, the presentation is meant to highlight a methodology of broad applicability. The example concerns an aircraft traveling from an origin point to a destination point in the presence of uncertain crosswinds and a low-connectivity zone that should be avoided. The MPC policy is parameterized by two hyperparameters, which are selected from data by the P2L procedure. Starting from a dataset of 400 wind realizations, also called scenarios, P2L identifies a final compression set containing only two informative scenarios. The resulting MPC policy avoids the low-connectivity zone on all available scenarios and, according to the P2L theory, satisfies a probabilistic risk bound of $4.8\%$ at confidence level $1-10^{-5}$, where the risk is the probability of entering the low-connectivity zone in a future flight under a new wind realization not included in the sample.

Problem

• Model Predictive Control
• Uncertain Crosswinds
• Low-connectivity Zone
• Probabilistic Risk Bound
• Origin-to-Destination Flight

Innovation

• Pick-to-Learn
• Model Predictive Control
• Scenario compression
• Probabilistic risk bound
• Calibration