Latent Dynamics-Aware OOD Monitoring for Trajectory Prediction with Provable Guarantees

2026-03-15

AI Summary

This work addresses the critical challenge of unreliable trajectory prediction in safety-critical cyber-physical systems under out-of-distribution (OOD) conditions. To this end, it introduces— for the first time—a hidden Markov model (HMM) framework for OOD monitoring, formulating the problem as quickest change-point detection. By modeling the latent dynamics of in-distribution prediction errors, the method integrates cumulative maximum mean discrepancy with statistical hypothesis testing to provide theoretical guarantees on both detection delay and false alarm rate, without requiring prior knowledge of the post-change distribution. Empirical evaluations on three real-world driving datasets demonstrate that the proposed approach significantly reduces detection latency while exhibiting strong robustness to heavy-tailed errors and unknown post-change conditions.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

In safety-critical Cyber-Physical Systems (CPS), accurate trajectory prediction provides vital guidance for downstream planning and control, yet although deep learning models achieve high-fidelity forecasts on validation data, their reliability degrades under out-of-distribution (OOD) scenarios caused by environmental uncertainty or rare traffic behaviors in real-world deployment; detecting such OOD events is challenging due to evolving traffic conditions and changing interaction patterns, while safety-critical applications demand formal guarantees on detection delay and false-alarm rates, motivating us-following recent work [1]-to formulate OOD monitoring for trajectory prediction as a quickest changepoint detection (QCD) problem that offers a principled statistical framework with established theory; we further observe that the real-world evolution of prediction errors under in-distribution (ID) conditions can be effectively modeled by a Hidden Markov Model (HMM), and by leveraging this structure we extend the cumulative Maximum Mean Discrepancy approach to enable detection without requiring explicit knowledge of the post-change distribution while still admitting provable guarantees on delay and false alarms, with experiments on three real-world driving datasets demonstrating reduced detection delay and robustness to heavy-tailed errors and unknown post-change conditions.

Problem

• out-of-distribution detection
• trajectory prediction
• quickest changepoint detection
• Cyber-Physical Systems
• safety-critical systems

Innovation

• Quickest Changepoint Detection
• Out-of-Distribution Monitoring
• Hidden Markov Model
• Maximum Mean Discrepancy
• Provable Guarantees