Waymax

The 'Waymax' dataset/benchmark is used to evaluate autonomous driving planners by providing scenarios that test their ability to safely navigate and correct unsafe actions during motion planning.

Papers using Waymax (5)

Mining the Long Tail: A Comparative Study of Data-Centric Criticality Metrics for Robust Offline Reinforcement Learning in Autonomous Motion Planning2025 · 3 citesCorrectionPlanner: Self-Correction Planner with Reinforcement Learning in Autonomous Driving2026V-Max: A Reinforcement Learning Framework for Autonomous Driving2025Physics-informed Imitative Reinforcement Learning for Real-world Driving2024Learning Multiple Probabilistic Decisions from Latent World Model in Autonomous Driving2024