A Multi-output Gaussian Process Regression with Negative Transfer Mitigation for Generating Boundary Test Scenarios of Multi-UAV Systems

TL;DR

This paper proposes a novel adaptive regularization approach into the conventional MOGPR training process that penalizes the inconsistencies among output-specific characteristic parameters using adaptively adjustable regularization weights and yields simultaneous improvements in predictive accuracy across all outputs.

Abstract

Adaptive sampling based on Gaussian process regression (GPR) has already been applied with considerable success to generate boundary test scenarios for multi-UAV systems (MUS). One of the key techniques in such researches is leveraging the accurate prediction of the MUS performance through GPR in different test scenarios. Due to the potential correlations among the multiple MUS performance metrics, current researches commonly utilize a multi-output GPR (MOGPR) to model the multiple performance metrics simultaneously. This approach can achieve a more accurate prediction, rather than modeling each metric individually. However, MOGPR still suffers from negative transfer. When the feature of one output variable is incorrectly learned by another, the models training process will be negatively affected, leading to a decline in prediction performance. To solve this problem, this paper proposes a novel adaptive regularization approach into the conventional MOGPR training process. Unlike existing regularization approaches for mitigating negative transfer in MOGPR, our method penalizes the inconsistencies among output-specific characteristic parameters using adaptively adjustable regularization weights. This mechanism helps each set of output parameters avoid local optima. Consequently, it yields simultaneous improvements in predictive accuracy across all outputs. Finally, we validate our approach on a numerical case and on a boundary test scenario generation case for a MUS multi-objectives search task.

Figures (24)

• Figure 1: Workflow for MOGPR-Based Adaptive Sampling to Generate Boundary Test Scenarios
• Figure 2: Graphical Model of the LMC
• Figure 3: Comparison of the Two Modeling Approaches. The results clearly indicate that individual modeling of each function significantly outperforms their joint analysis. This is particularly evident for y1.
• Figure 4: Output-Specific Characteristic Parameters Sharing Mechanism
• Figure 5: Iterations to Start Regularization