Motion Planning on nuPlan 14-hard (test)
90.15NRPDM-Closed
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| PDM-ClosedType=Rule-based & Hybrid2026.03 | 90.15 | — | 76.19 | |
| Log-replayType=Expert2026.03 | 85.96 | — | 68.8 | |
| PLUTOType=Rule-based & Hybrid2026.03 | 80.08 | — | 76.88 | |
| TDDMType=Learning-based2026.03 | 77.95 | — | 65.2 | |
| Diffusion PlannerType=Learning-based2026.03 | 75.67 | — | 68.56 | |
| PLUTO w/o refine.Type=Learning-based2026.03 | 70.03 | — | 59.74 | |
| PlanTFType=Learning-based2026.03 | 69.7 | — | 61.61 | |
| GameFormerType=Rule-based & Hybrid2026.03 | 68.7 | — | 70.05 | |
| PDM-HybridType=Rule-based & Hybrid2026.03 | 65.99 | — | 70.92 | |
| IDMType=Rule-based & Hybrid2026.03 | 56.15 | — | 62.26 | |
| UrbanDriverType=Learning-based2026.03 | 50.4 | — | 49.95 | |
| PDM-OpenType=Learning-based2026.03 | 33.51 | — | 33.89 | |
| BIBeRIntegration=Co-Leader, Evaluation Setting=SMART Reactive2025.12 | — | 75.72 | — | |
| DiffusionPlannerIntegration=Joint, Evaluation Setting=SMART Reactive2025.12 | — | 63.09 | — | |
| DTPPIntegration=Co-Leader, Evaluation Setting=SMART Reactive2025.12 | — | 46.65 | — | |
| GameFormerIntegration=Joint, Evaluation Setting=SMART Reactive2025.12 | — | 62.48 | — | |
| GC-PGPIntegration=None, Evaluation Setting=SMART Reactive2025.12 | — | 40.96 | — | |
| PDM-ClosedIntegration=Human Leader, Evaluation Setting=SMART Reactive2025.12 | — | 73.99 | — | |
| PDM-HybridIntegration=Human Leader, Evaluation Setting=SMART Reactive2025.12 | — | 72.15 | — | |
| PDM-OpenIntegration=None, Evaluation Setting=SMART Reactive2025.12 | — | 38.1 | — | |
| PlanCNNIntegration=None, Evaluation Setting=SMART Reactive2025.12 | — | 50.78 | — | |
| PlanTFIntegration=None, Evaluation Setting=SMART Reactive2025.12 | — | 57.5 | — | |
| Urban DriverIntegration=None, Evaluation Setting=SMART Reactive2025.12 | — | 38.38 | — |