Building Real-time Awareness of Out-of-distribution in Trajectory Prediction for Autonomous Vehicles
Open Access
- 26 March 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Cyber-Physical Systems
Abstract
Embodied AI systems operate in a closed perception-action loop. In many safety-critical applications, embodied AI systems must adapt to highly uncertain and dynamically evolving environments. In the context of autonomous vehicles, trustworthy trajectory prediction is therefore a prerequisite for safe interaction with surrounding agents and infrastructure. In practice, however, even well-trained machine learning models may produce unreliable predictions. Such sim-to-real gaps (also known as imperfect training data) may be unavoidable due to the overwhelming complexity of data annotation and environment uncertainties. To ensure safety, it is critical to quickly detect when a model's predictions become unreliable. Leveraging the intuition that in-distribution (ID) scenes exhibit error patterns similar to training data, while out-of-distribution (OOD) scenes do not, we introduce a principled and computationally efficient approach for OOD detection by framing it as a quickest change-point detection problem. We address the challenging settings where the OOD scenes are deceptive, meaning that they are not easily detectable by human intuitions. Our solutions can handle the occurrence of OOD at any time during trajectory prediction inference. Experimental results on multiple real-world datasets demonstrate the effectiveness of our methods.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Uncertainty Quantification for Safe and Reliable Autonomous Vehicles: A Review of Methods and ApplicationsIEEE Transactions on Intelligent Transportation Systems, 2025
- Unravelling uncertainty in trajectory prediction using a non-parametric approachTransportation Research Part C: Emerging Technologies, 2024
- Predicting neural network confidence using high-level feature distanceInformation and Software Technology, 2023
- A Kinematic Model for Trajectory Prediction in General Highway ScenariosIEEE Robotics and Automation Letters, 2021
- Deep Inverse Reinforcement Learning for Behavior Prediction in Autonomous Driving: Accurate Forecasts of Vehicle MotionIEEE Signal Processing Magazine, 2020
- GRIP: Graph-based Interaction-aware Trajectory Prediction2019
- How Would Surround Vehicles Move? A Unified Framework for Maneuver Classification and Motion PredictionIEEE Transactions on Intelligent Vehicles, 2018
- Misspecified and Asymptotically Minimax Robust Quickest Change DetectionIEEE Transactions on Signal Processing, 2017
- Nonstationary Z-Score measuresEuropean Journal of Operational Research, 2017
- Vehicle dynamics and external disturbance estimation for vehicle path predictionIEEE Transactions on Control Systems Technology, 2000