Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research

TL;DR

Waymax is a fast, data-driven autonomous driving simulator leveraging real-world datasets and hardware acceleration, enabling large-scale, realistic multi-agent scenario testing for training and benchmarking planning algorithms.

Contribution

Introduces Waymax, a novel large-scale, data-driven simulator for autonomous driving that supports hardware acceleration and realistic multi-agent interactions.

Findings

Waymax effectively utilizes real-world data for simulation.

Hardware acceleration enables large-scale, real-time simulation.

Benchmarking shows RL algorithms can overfit in simulation.

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.