Pseudo-Simulation for Autonomous Driving

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cao, Wei, Hallgarten, Marcel, Li, Tianyu, Dauner, Daniel, Gu, Xunjiang, Wang, Caojun, Miron, Yakov, Aiello, Marco, Li, Hongyang, Gilitschenski, Igor, Ivanovic, Boris, Pavone, Marco, Geiger, Andreas, Chitta, Kashyap
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914410580148224
author Cao, Wei
Hallgarten, Marcel
Li, Tianyu
Dauner, Daniel
Gu, Xunjiang
Wang, Caojun
Miron, Yakov
Aiello, Marco
Li, Hongyang
Gilitschenski, Igor
Ivanovic, Boris
Pavone, Marco
Geiger, Andreas
Chitta, Kashyap
author_facet Cao, Wei
Hallgarten, Marcel
Li, Tianyu
Dauner, Daniel
Gu, Xunjiang
Wang, Caojun
Miron, Yakov
Aiello, Marco
Li, Hongyang
Gilitschenski, Igor
Ivanovic, Boris
Pavone, Marco
Geiger, Andreas
Chitta, Kashyap
contents Existing evaluation paradigms for Autonomous Vehicles (AVs) face critical limitations. Real-world evaluation is often challenging due to safety concerns and a lack of reproducibility, whereas closed-loop simulation can face insufficient realism or high computational costs. Open-loop evaluation, while being efficient and data-driven, relies on metrics that generally overlook compounding errors. In this paper, we propose pseudo-simulation, a novel paradigm that addresses these limitations. Pseudo-simulation operates on real datasets, similar to open-loop evaluation, but augments them with synthetic observations generated prior to evaluation using 3D Gaussian Splatting. Our key idea is to approximate potential future states the AV might encounter by generating a diverse set of observations that vary in position, heading, and speed. Our method then assigns a higher importance to synthetic observations that best match the AV's likely behavior using a novel proximity-based weighting scheme. This enables evaluating error recovery and the mitigation of causal confusion, as in closed-loop benchmarks, without requiring sequential interactive simulation. We show that pseudo-simulation is better correlated with closed-loop simulations ($R^2=0.8$) than the best existing open-loop approach ($R^2=0.7$). We also establish a public leaderboard for the community to benchmark new methodologies with pseudo-simulation. Our code is available at https://github.com/autonomousvision/navsim.
format Preprint
id arxiv_https___arxiv_org_abs_2506_04218
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pseudo-Simulation for Autonomous Driving
Cao, Wei
Hallgarten, Marcel
Li, Tianyu
Dauner, Daniel
Gu, Xunjiang
Wang, Caojun
Miron, Yakov
Aiello, Marco
Li, Hongyang
Gilitschenski, Igor
Ivanovic, Boris
Pavone, Marco
Geiger, Andreas
Chitta, Kashyap
Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Existing evaluation paradigms for Autonomous Vehicles (AVs) face critical limitations. Real-world evaluation is often challenging due to safety concerns and a lack of reproducibility, whereas closed-loop simulation can face insufficient realism or high computational costs. Open-loop evaluation, while being efficient and data-driven, relies on metrics that generally overlook compounding errors. In this paper, we propose pseudo-simulation, a novel paradigm that addresses these limitations. Pseudo-simulation operates on real datasets, similar to open-loop evaluation, but augments them with synthetic observations generated prior to evaluation using 3D Gaussian Splatting. Our key idea is to approximate potential future states the AV might encounter by generating a diverse set of observations that vary in position, heading, and speed. Our method then assigns a higher importance to synthetic observations that best match the AV's likely behavior using a novel proximity-based weighting scheme. This enables evaluating error recovery and the mitigation of causal confusion, as in closed-loop benchmarks, without requiring sequential interactive simulation. We show that pseudo-simulation is better correlated with closed-loop simulations ($R^2=0.8$) than the best existing open-loop approach ($R^2=0.7$). We also establish a public leaderboard for the community to benchmark new methodologies with pseudo-simulation. Our code is available at https://github.com/autonomousvision/navsim.
title Pseudo-Simulation for Autonomous Driving
topic Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2506.04218