Saved in:
Bibliographic Details
Main Authors: Guo, Tongfei, Su, Lili
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.14603
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910053942951936
author Guo, Tongfei
Su, Lili
author_facet Guo, Tongfei
Su, Lili
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14603
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Latent Dynamics-Aware OOD Monitoring for Trajectory Prediction with Provable Guarantees
Guo, Tongfei
Su, Lili
Robotics
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.
title Latent Dynamics-Aware OOD Monitoring for Trajectory Prediction with Provable Guarantees
topic Robotics
url https://arxiv.org/abs/2603.14603