Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research
Abstract
Simulation is an essential tool to develop and benchmark autonomous vehicle planning software in a safe and cost-effective manner. However, realistic simulation requires accurate modeling of nuanced and complex multi-agent interactive behaviors. To address these challenges, we introduce Waymax, a new data-driven simulator for autonomous driving in multi-agent scenes, designed for large-scale simulation and testing. Waymax uses publicly-released, real-world driving data (e.g., the Waymo Open Motion Dataset) to initialize or play back a diverse set of multi-agent simulated scenarios. It runs entirely on hardware accelerators such as TPUs/GPUs and supports in-graph simulation for training, making it suitable for modern large-scale, distributed machine learning workflows. To support online training and evaluation, Waymax includes several learned and hard-coded behavior models that allow for realistic interaction within simulation. To supplement Waymax, we benchmark a suite of popular imitation and reinforcement learning algorithms with ablation studies on different design decisions, where we highlight the effectiveness of routes as guidance for planning agents and the ability of RL to overfit against simulated agents.
Cite
@article{arxiv.2310.08710,
title = {Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research},
author = {Cole Gulino and Justin Fu and Wenjie Luo and George Tucker and Eli Bronstein and Yiren Lu and Jean Harb and Xinlei Pan and Yan Wang and Xiangyu Chen and John D. Co-Reyes and Rishabh Agarwal and Rebecca Roelofs and Yao Lu and Nico Montali and Paul Mougin and Zoey Yang and Brandyn White and Aleksandra Faust and Rowan McAllister and Dragomir Anguelov and Benjamin Sapp},
journal= {arXiv preprint arXiv:2310.08710},
year = {2023}
}