Credible Uncertainty Quantification under Noise and System Model Mismatch
This provides a practical tool for diagnosing model deficiencies in state estimation, which is critical for downstream tasks, though it appears incremental as it builds on existing metrics.
The paper tackled the problem of misleading self-assessed uncertainty metrics in state estimators due to noise or system model mismatches, by developing a multi-metric framework that achieved 80-100% diagnosis accuracy in simulations and was validated on real-world data.
State estimators often provide self-assessed uncertainty metrics, such as covariance matrices, whose credibility is critical for downstream tasks. However, these self-assessments can be misleading due to underlying modeling violations like noise model mismatch (NMM) or system model misspecification (SMM). This letter addresses this problem by developing a unified, multi-metric framework that integrates noncredibility index (NCI), negative log-likelihood (NLL), and energy score (ES) metrics, featuring an empirical location test (ELT) to detect system model bias and a directional probing technique that uses the metrics' asymmetric sensitivities to distinguish NMM from SMM. Monte Carlo simulations reveal that the proposed method achieves excellent diagnosis accuracy (80-100%) and significantly outperforms single-metric diagnosis methods. The effectiveness of the proposed method is further validated on a real-world UWB positioning dataset. This framework provides a practical tool for turning patterns of credibility indicators into actionable diagnoses of model deficiencies.