Yinan Zheng*, Ruiming Liang*, Kexin Zheng*, Jinliang Zheng, Liyuan Mao, Jianxiong Li, Weihao Gu, Rui Ai, Shengbo Eben Li, Xianyuan Zhan, Jingjing Liu
Paper & code comming soon
The official implementation of Diffusion Planner, which represents a pioneering effort in fully harnessing the power of diffusion models for high-performance motion planning, without overly relying on refinement.
Diffusion Planner leverages the expressive and flexible diffusion model to enhance autonomous planning:
- DiT-based architecture focusing on the fusion of noised future vehicle trajectories and conditional information
- Joint modeling of key participants' statuses, unifying motion prediction and closed-loop planning as future trajectory generation
- Fast inference during diffusion sampling, achieving around 20Hz for real-time performance
| Methods | Val14 (NR) | Val14 (R) | Test14-hard (NR) | Test14-hard (R) | Test14 (NR) | Test14 (R) |
|---|---|---|---|---|---|---|
| PDM-Open* | 53.53 | 54.24 | 33.51 | 35.83 | 52.81 | 57.23 |
| UrbanDriver | 68.57 | 64.11 | 50.40 | 49.95 | 51.83 | 67.15 |
| GameFormer w/o refine. | 13.32 | 8.69 | 7.08 | 6.69 | 11.36 | 9.31 |
| PlanTF | 84.72 | 76.95 | 69.70 | 61.61 | 85.62 | 79.58 |
| PLUTO w/o refine.* | 88.89 | 78.11 | 70.03 | 59.74 | 89.90 | 78.62 |
| Diffusion-es w/o LLM | 50.00 | - | - | - | - | - |
| STR2-CPKS-800M w/o refine.* | 8.80 | - | 10.99 | - | - | - |
| Diffusion Planner (ours) | 89.76 | 82.56 | 75.67 | 68.56 | 89.22 | 83.36 |
*: Using pre-searched reference lines or additional proposals as model inputs provides prior knowledge.
| Methods | Val14 (NR) | Val14 (R) | Test14-hard (NR) | Test14-hard (R) | Test14 (NR) | Test14 (R) |
|---|---|---|---|---|---|---|
| Expert (Log-replay) | 93.53 | 80.32 | 85.96 | 68.80 | 94.03 | 75.86 |
| IDM | 75.60 | 77.33 | 56.15 | 62.26 | 70.39 | 74.42 |
| PDM-Closed | 92.84 | 92.12 | 65.08 | 75.19 | 90.05 | 91.63 |
| PDM-Hybrid | 92.77 | 92.11 | 65.99 | 76.07 | 90.10 | 91.28 |
| GameFormer | 79.94 | 79.78 | 68.70 | 67.05 | 83.88 | 82.05 |
| PLUTO | 92.88 | 76.88 | 80.08 | 76.88 | 92.23 | 90.29 |
| Diffusion-es | 92.00 | - | - | - | - | - |
| STR2-CPKS-800M | 93.91 | 92.51 | 77.54 | 82.02 | - | - |
| Diffusion Planner w/ refine (ours) | 94.26 | 92.90 | 78.87 | 82.00 | 94.80 | 91.75 |
Future trajectory generation visualization. A frame from a challenging narrow road turning scenario in the closed-loop test, including the future planning of the ego vehicle (PlanTF and PLUTO w/o refine. showing multiple candidate trajectories), predictions for neighboring vehicles, and the ground truth ego trajectory.
Diffusion Planner is greatly inspired by the following outstanding contributions to the open-source community: nuplan-devkit, GameFormer-Planner, tuplan_garage, planTF, pluto, StateTransformer, DiT, dpm-solver