# Scalable Offline Metrics for Autonomous Driving

arXiv: https://arxiv.org/abs/2510.08571 · HTML: https://mlsanity.com/paper/2510.08571/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in End-to-end system architecture, one of 9 directions in End-to-end autonomous driving.
- Builds on 50 of its 72 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Placed in

- End-to-end autonomous driving / [End-to-end system architecture](https://mlsanity.com/driving/end-to-end-system-architecture/)

## Builds on (most cited first, 30 of 50)

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [VAD: Vectorized Scene Representation for Efficient Autonomous Driving](https://mlsanity.com/paper/2303.12077/) (2023)
- [End-to-end Driving via Conditional Imitation Learning](https://mlsanity.com/paper/1710.02410/) (2017)
- [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2205.15997/) (2022)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst](https://mlsanity.com/paper/1812.03079/) (2018)
- [Learning by Cheating](https://mlsanity.com/paper/1912.12294/) (2019)
- [Multi-Modal Fusion Transformer for End-to-End Autonomous Driving](https://mlsanity.com/paper/2104.09224/) (2021)
- [ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning](https://mlsanity.com/paper/2207.07601/) (2022)
- [NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking](https://mlsanity.com/paper/2406.15349/) (2024)
- [Learning to Drive in a Day](https://mlsanity.com/paper/1807.00412/) (2018)
- [Parting with Misconceptions about Learning-based Vehicle Motion Planning](https://mlsanity.com/paper/2306.07962/) (2023)
- [Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?](https://mlsanity.com/paper/2312.03031/) (2023)
- [Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer](https://mlsanity.com/paper/2207.14024/) (2022)
- [DART: Noise Injection for Robust Imitation Learning](https://mlsanity.com/paper/1703.09327/) (2017)
- [End-to-end Learning of Driving Models from Large-scale Video Datasets](https://mlsanity.com/paper/1612.01079/) (2016)
- [Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?](https://mlsanity.com/paper/2006.14911/) (2020)
- [AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles](https://mlsanity.com/paper/2101.06549/) (2021)
- [LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving](https://mlsanity.com/paper/2101.06547/) (2021)
- [KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients](https://mlsanity.com/paper/2204.13683/) (2022)
- [Hidden Biases of End-to-End Driving Models](https://mlsanity.com/paper/2306.07957/) (2023)

## Abstract (arXiv)

Real-world evaluation of perception-based planning models for robotic systems, such as autonomous vehicles, can be safely and inexpensively conducted offline, i.e. by computing model prediction error over a pre-collected validation dataset with ground-truth annotations. However, extrapolating from offline model performance to online settings remains a challenge. In these settings, seemingly minor errors can compound and result in test-time infractions or collisions. This relationship is understudied, particularly across diverse closed-loop metrics and complex urban maneuvers. In this work, we revisit this undervalued question in policy evaluation through an extensive set of experiments across diverse conditions and metrics. Based on analysis in simulation, we find an even worse correlation between offline and online settings than reported by prior studies, casting doubts on the validity of current evaluation practices and metrics for driving policies. Next, we bridge the gap between offline and online evaluation. We investigate an offline metric based on epistemic uncertainty, which aims to capture events that are likely to cause errors in closed-loop settings. The resulting metric achieves over 13% improvement in correlation compared to previous offline metrics. We further validate the generalization of our findings beyond the simulation environment in real-world settings, where even greater gains are observed.