Confidence-Aware Learning Optimal Terminal Guidance via Gaussian Process Regression

TL;DR

The paper addresses constrained optimal terminal guidance by coupling region-controlled data generation with confidence-aware learning. It introduces a state-transition-matrix–guided backward data generation method to produce well-distributed optimal trajectories within a predefined region, and an error-distribution-smoothing filter to reduce data volume by about 90% without sacrificing accuracy. A Gaussian Process Regression framework then provides predictive guidance with quantified uncertainty, blended with an analytical baseline when confidence is low. Numerical simulations on impact-angle/time control validate data controllability, efficiency, and reliability, demonstrating extended applicability of learned strategies beyond training regimes.

Abstract

Modern aerospace guidance systems demand rigorous constraint satisfaction, optimal performance, and computational efficiency. Traditional analytical methods struggle to simultaneously satisfy these requirements. While data driven methods have shown promise in learning optimal guidance strategy, challenges still persist in generating well-distributed optimal dataset and ensuring the reliability and trustworthiness of learned strategies. This paper presents a confidence-aware learning framework that addresses these limitations. First, a region-controllable optimal data generation method is proposed leveraging Hamiltonian state transition matrices, enabling efficient generation of optimal trajectories of specified data distribution. Then, to obtain a lightweight and effective dataset for efficient strategy learning, an error-distribution-smoothing method is incorporated to employ data filtering, which reduces dataset size by almost 90% while preserving prediction accuracy. To assess the operational domain of the learned strategy, a confidence-aware learning guidance strategy is proposed based on gaussian process regression, achieving constraint satisfaction even beyond training distributions. Numerical simulations validate the effectiveness and reliability of the proposed learning framework in terms of data generation, data filtering and strategy learning.

Figures (9)

• Figure 1: Planar engagement geometry
• Figure 2: Dimensionality reduction by symmetry
• Figure 3: Diagram of confidence-aware learning framework
• Figure 4: Comparison of initial state regions
• Figure 5: Data filtering by the error distribution smoothing method