Open-loop Autonomous Driving on NAVSIM (val)
98.6NCiPad
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| iPadInput=Camera, Backbone=ResNet-342025.05 | 98.6 | 98.3 | 94.9 | 100 | 88 | 91.7 | |
| Hydra-MDP-V8192-W-EPInput=Camera & Lidar, Backbone=ResNet-342025.05 | 98.3 | 96 | 94.6 | 100 | 78.7 | 86.5 | |
| DiffusionDriveInput=Camera & Lidar, Backbone=ResNet-342025.05 | 98.2 | 96.2 | 94.7 | 100 | 82.2 | 88.1 | |
| DRAMAInput=Camera & Lidar, Backbone=ResNet-342025.05 | 98 | 93.1 | 94.8 | 100 | 80.1 | 85.5 | |
| PARA-DriveInput=Camera, Backbone=ResNet-342025.05 | 97.9 | 92.4 | 93 | 99.8 | 79.3 | 84 | |
| UniADInput=Camera, Backbone=ResNet-342025.05 | 97.8 | 91.9 | 92.9 | 100 | 78.8 | 83.4 | |
| TransfuserInput=Camera & Lidar, Backbone=ResNet-342025.05 | 97.7 | 92.8 | 92.8 | 100 | 79.2 | 84 | |
| LTFInput=Camera, Backbone=ResNet-342025.05 | 97.4 | 92.8 | 92.4 | 100 | 79 | 83.8 | |
| VADV2-V8192Input=Camera & Lidar, Backbone=ResNet-342025.05 | 97.2 | 89.1 | 91.6 | 100 | 76 | 80.9 | |
| PDM-Closed (Rule-based)Input=Perception GT, Backbone=None2025.05 | 94.6 | 99.8 | 86.9 | 99.9 | 89.9 | 89.1 |