Summary: End-to-End
Contents
| Title | Link | Date | Conference | Institution |
|---|---|---|---|---|
| vad | arXiv GitHub | |||
| vadv2 | arXiv GitHub | |||
| Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation | arXiv GitHub | 2024.06 | The 1st place solution of End-to-end Driving at Scale at the CVPR 2024 Autonomous Grand Challenge | NVIDIA |
| Hydra-MDP++: | arXiv GitHub | 2025.03 | NVIDIA | |
| World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model | arXiv GitHub | 2025.03 | ICLR | Li Auto |
| WoTE: End-to-End Driving with Online Trajectory Evaluation via BEV World Model | arXiv GitHub |
| Dataset Name | Release Date | Organization | Link |
|---|---|---|---|
| NAVSIM | based on nuPlan | ||
| Bench2Drive |
NAVSIM Predictive Driver Model Score (PDMS): - No At-Fault Collision (NC) - Drivable Area Compliance (DAC) - Time-to-Collision (TTC) - Comfort (Comf.) - Ego Progress (EP)
Bench2Drive Driving Score (DS) success rate