RDS-DeePC: Robust Data Selection for Data-Enabled Predictive Control via Sensitivity Score
This addresses computational and robustness issues in model-free predictive control for systems like UAVs and vehicles, but it is incremental as it builds on existing DeePC methods.
The paper tackles the computational complexity and performance degradation from corrupted data in Data-Enabled Predictive Control by introducing RDS-DeePC, which uses sensitivity scores to select low-sensitivity data segments, achieving 94-97% clean data selection and comparable or better tracking performance under 20% data corruption.
Data Enabled Predictive Control (DeePC) is an established model free approach to predictive control, but it faces two open challenges: computational complexity that scales cubically with dataset size and performance degradation when data are corrupted. This paper introduces Robust Data Selection DeePC (RDS DeePC), a framework that addresses both obstacles through influence function analysis. We derive a sensitivity score quantifying the leverage each trajectory segment exerts on the optimization solution and prove that high sensitivity segments correspond to outliers while low sensitivity segments represent consistent data. Selecting low sensitivity segments thus yields both computational efficiency and automatic outlier filtering without requiring data quality labels. For nonlinear systems, we extend the framework via a two stage online selection approach accelerated by the LiSSA algorithm. Experiments on four systems of increasing complexity including a DC motor, an inverted pendulum, a planar quadrotor UAV tracking a figure 8 trajectory, and a kinematic bicycle vehicle following a figure 8 path demonstrate that RDS DeePC achieves 94 to 97 percent clean data selection and comparable or better tracking performance under 20 percent data corruption.