Hierarchical Causal Abduction: A Foundation Framework for Explainable Model Predictive Control

TL;DR

This paper introduces Hierarchical Causal Abduction (HCA), a framework combining physics-informed reasoning, optimization evidence, and causal discovery to generate interpretable explanations for nonlinear MPC in safety-critical systems.

Contribution

HCA is a novel framework that integrates multiple evidence sources to produce faithful, human-interpretable explanations for control actions in nonlinear MPC, outperforming existing methods.

Findings

HCA improves explanation accuracy by 53% over LIME across three applications.

Domain-specific calibration increases explanation accuracy to 0.88.

Each evidence source is essential; removing any reduces accuracy by 32-37%.

Abstract

Model Predictive Control (MPC) is widely used to operate safety-critical infrastructure by predicting future trajectories and optimizing control actions. However, nonlinear dynamics, hard safety constraints, and numerical optimization often render individual control moves opaque to human operators, undermining trust and hindering deployment. This paper presents Hierarchical Causal Abduction (HCA), which combines (i) physics-informed reasoning via domain knowledge graphs, (ii) optimization evidence from Karush--Kuhn--Tucker (KKT) multipliers, and (iii) temporal causal discovery via the PCMCI algorithm to generate faithful, human-interpretable explanations for control actions computed by nonlinear MPC. Across three diverse control applications (greenhouse climate, building HVAC, chemical process engineering) with expert validation, HCA improves explanation accuracy by 53\% over LIME (0.478 vs. 0.311) using a single set of cross-domain parameters without per-domain tuning; domain-specific KKT-threshold calibration over 2--3 days further increases accuracy to 0.88. Ablation studies confirm that each evidence source is essential, with 32--37\% accuracy degradation when any component is removed, and HCA's ranking-and-validation methodology generalizes beyond MPC to other prediction-based decision systems, including learning-based control and trajectory planning.