NAVSIMv-2

NAVSIMv2 is a dataset/benchmark used to evaluate the performance of end-to-end autonomous driving systems by providing a set of scenarios and metrics for assessing imitation and reinforcement learning approaches.

Papers using NAVSIMv-2 (4)

WAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving2025Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving2026DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving2026IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model2025