Scalable Offline Metrics for Autonomous Driving

• URL: http://arxiv.org/abs/2510.08571v2
• Date: Mon, 10 Nov 2025 03:22:29 GMT
• Title: Scalable Offline Metrics for Autonomous Driving
• Authors: Animikh Aich, Adwait Kulkarni, Eshed Ohn-Bar,
• Abstract summary: Extrapolating from offline model performance to online settings remains a challenge.<n>In these settings, seemingly minor errors can compound and result in test-time infractions or collisions.<n>Based on analysis in simulation, we find an even worse correlation between offline and online settings than reported by prior studies.
• Score: 12.613436727986652
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Learning Shortest Paths When Data is Scarce [3.3012620893449465]
  We study a shortest-path problem in which a planner has access to abundant synthetic samples, limited real-world observations, and an edge-similarity capturing expected behavioral similarity across links.<n>We model the simulator-to-reality discrepancy as an unknown, edge-specific bias that varies smoothly over the similarity graph, and estimate it using Laplacian-regularized least squares.<n>For cold-start settings without initial real data, we develop a bias-aware active learning algorithm that adaptively selects edges to measure until a prescribed accuracy is met.
  arXiv  Detail & Related papers  (2026-01-07T06:19:04Z)
• Uncertainty Guided Online Ensemble for Non-stationary Data Streams in Fusion Science [3.6886967341942785]
  We present an application of online learning to continuously adapt to drifting data stream for prediction of Toroidal Field coils deflection.<n>Traditional online learning can suffer from short-term performance degradation as ground truth is not available before making predictions.<n>We propose an uncertainty guided online ensemble method to further improve the performance.
  arXiv  Detail & Related papers  (2025-11-03T22:03:37Z)
• Position: All Current Generative Fidelity and Diversity Metrics are Flawed [58.815519650465774]
  We show that all current generative fidelity and diversity metrics are flawed.<n>Our aim is to convince the research community to spend more effort in developing metrics, instead of models.
  arXiv  Detail & Related papers  (2025-05-28T15:10:33Z)
• The Effects of Data Split Strategies on the Offline Experiments for CTR Prediction [0.0]
  This study aims to address the inconsistency between current offline evaluation methods and real-world use cases. We conduct extensive experiments using both random and temporal splits on a large open benchmark dataset, Criteo.
  arXiv  Detail & Related papers  (2024-06-26T13:01:52Z)
• NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking [65.24988062003096]
  We present NAVSIM, a framework for benchmarking vision-based driving policies. Our simulation is non-reactive, i.e., the evaluated policy and environment do not influence each other. NAVSIM enabled a new competition held at CVPR 2024, where 143 teams submitted 463 entries, resulting in several new insights.
  arXiv  Detail & Related papers  (2024-06-21T17:59:02Z)
• Improving Offline Reinforcement Learning with Inaccurate Simulators [34.54402525918925]
  We propose a novel approach to combine the offline dataset and the inaccurate simulation data in a better manner. Specifically, we pre-train a generative adversarial network (GAN) model to fit the state distribution of the offline dataset. Our experimental results in the D4RL benchmark and a real-world manipulation task confirm that our method can benefit more from both inaccurate simulator and limited offline datasets to achieve better performance than the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-07T13:29:41Z)
• Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving? [84.17711168595311]
  End-to-end autonomous driving has emerged as a promising research direction to target autonomy from a full-stack perspective. nuScenes dataset, characterized by relatively simple driving scenarios, leads to an under-utilization of perception information in end-to-end models. We introduce a new metric to evaluate whether the predicted trajectories adhere to the road.
  arXiv  Detail & Related papers  (2023-12-05T11:32:31Z)
• Navigating the Noise: Bringing Clarity to ML Parameterization Design with O(100) Ensembles [1.9199275795132604]
  Machine-learning (ML) parameterizations of subgrid processes may one day replace conventional parameterizations.<n>Uncertainty about the relationship between offline and online performance hinders their development.<n>We show how systematic reductions in offline error manifest in changes to online error and online stability.
  arXiv  Detail & Related papers  (2023-09-28T05:34:29Z)
• Exploring validation metrics for offline model-based optimisation with diffusion models [50.404829846182764]
  In model-based optimisation (MBO) we are interested in using machine learning to design candidates that maximise some measure of reward with respect to a black box function called the (ground truth) oracle. While an approximation to the ground oracle can be trained and used in place of it during model validation to measure the mean reward over generated candidates, the evaluation is approximate and vulnerable to adversarial examples. This is encapsulated under our proposed evaluation framework which is also designed to measure extrapolation.
  arXiv  Detail & Related papers  (2022-11-19T16:57:37Z)
• Injecting Planning-Awareness into Prediction and Detection Evaluation [42.228191984697006]
  We take a step back and critically assess current evaluation metrics, proposing task-aware metrics as a better measure of performance in systems where they are deployed. Experiments on an illustrative simulation as well as real-world autonomous driving data validate that our proposed task-aware metrics are able to account for outcome asymmetry and provide a better estimate of a model's closed-loop performance.
  arXiv  Detail & Related papers  (2021-10-07T08:52:48Z)
• A Unified Framework for Online Trip Destination Prediction [7.34084539365505]
  Trip destination prediction is an area of increasing importance in many applications such as trip planning and autonomous driving. We present a unified framework for trip destination prediction in an online setting, which is suitable for both online training and online prediction.
  arXiv  Detail & Related papers  (2021-01-12T14:45:27Z)
• Do Offline Metrics Predict Online Performance in Recommender Systems? [79.48653445643865]
  We investigate the extent to which offline metrics predict online performance by evaluating recommenders across six simulated environments. We observe that offline metrics are correlated with online performance over a range of environments. We study the impact of adding exploration strategies, and observe that their effectiveness, when compared to greedy recommendation, is highly dependent on the recommendation algorithm.
  arXiv  Detail & Related papers  (2020-11-07T01:41:13Z)
• Provably Efficient Causal Reinforcement Learning with Confounded Observational Data [135.64775986546505]
  We study how to incorporate the dataset (observational data) collected offline, which is often abundantly available in practice, to improve the sample efficiency in the online setting. We propose the deconfounded optimistic value iteration (DOVI) algorithm, which incorporates the confounded observational data in a provably efficient manner.
  arXiv  Detail & Related papers  (2020-06-22T14:49:33Z)
• AliExpress Learning-To-Rank: Maximizing Online Model Performance without Going Online [60.887637616379926]
  This paper proposes an evaluator-generator framework for learning-to-rank. It consists of an evaluator that generalizes to evaluate recommendations involving the context, and a generator that maximizes the evaluator score by reinforcement learning. Our method achieves a significant improvement in terms of Conversion Rate (CR) over the industrial-level fine-tuned model in online A/B tests.
  arXiv  Detail & Related papers  (2020-03-25T10:27:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.