Efficient World-Model Planning via Physics-Guided Search Distillation
Organizations: Yanshan University · Xiaomi Corporation · KAIST · Tsinghua University ·
Abstract
World models support autonomous driving by evaluating candidate trajectories through predicted future scene evolution. However, accurate future prediction does not ensure road-compliant execution; when all candidates violate road boundaries, re-ranking cannot select a feasible trajectory. We propose Physics-Guided Search Distillation (PGSD), a single-view planning framework that combines future representations and execution feedback for verified beyond-pool repair through three components: (1) Execution-Aware Selection checks ego-vehicle road compliance under simulated execution and selects the highest-scoring feasible trajectory; (2) a Clearance-Aware Search Teacher generates beyond-pool corrections and selects demonstrations with larger minimum road-boundary clearance during execution to buffer imitation errors; and (3) a Future-Conditioned Repair Student predicts one correction from rewarder features and execution feedback for single-rollout verification. The pretrained planner and rewarder remain frozen; no future scenes are generated online. On NAVSIM v1, single-view PGSD achieves 90.97 PDMS, exceeding all compared prior single-view planners and retaining 73.2% of the search teacher's PDMS gain over execution-aware selection. On NAVSIM v2 navhard, it reaches 38.96 EPDMS, improving on WorldDrive by 11.24 points (40.5%). The student replaces up to ten search rollouts with a single verification rollout per repair trigger. HUGSIM Hard examples provide qualitative evidence of zero-shot transfer.
Figures & tables
| Method | Sensors | World model | NC | DAC | TTC | Comf. | EP | PDMS | PDMS |
| TransFuser [ 36 ] | MV & L | 97.7 | 92.8 | 92.8 | 100.0 | 79.2 | 84.0 | -5.0 | |
| Hydra-MDP [ 32 ] | MV & L | 98.3 | 96.0 | 94.6 | 100.0 | 78.7 | 86.5 | -2.5 | |
| DiffusionDrive [ 3 ] | MV & L | 98.2 | 96.2 | 94.7 | 100.0 | 82.2 | 88.1 | -0.9 | |
| WoTE [ 6 ] | MV & L | 98.5 | 96.8 | 94.9 | 99.9 | 81.9 | 88.3 | -0.7 | |
| UniAD [ 1 ] | MV | 97.8 | 91.9 | 92.9 | 100.0 | 78.8 | 83.4 | -5.6 | |
| PARA-Drive [ 37 ] | MV | 97.9 | 92.4 | 93.0 | 99.8 | 79.3 | 84.0 | -5.0 |
| Method | Sensors | Stage | NC | DAC | EP | TTC | HC | EPDMS |
|---|---|---|---|---|---|---|---|---|
| LTF | MV | S1 | 96.2 | 79.5 | 84.1 | 95.1 | 97.5 | 23.1 |
| S2 | 77.7 | 70.2 | 85.1 | 75.6 | 95.7 | |||
| DiffusionDrive | MV | S1 | 96.8 | 86.0 | 84.0 | 95.8 | 97.6 | 27.5 |
| S2 | 80.1 | 72.8 | 85.9 | 76.6 | 96.3 | |||
| WorldDrive | SV | S1 | 95.7 | 80.4 | 81.8 | 94.4 | 97.6 | 27.72 |
| S2 | 82.9 | 68.0 | 81.6 | 78.2 | 97.4 |
| Method | EAS | Repair | FAR student | SRV | DAC | EP | PDMS |
| Component variants | |||||||
| WorldDrive | — | None | — | — | 97.0 | 83.5 | 89.0 |
| + EAS | None | — | — | 98.4 | 84.6 | 90.4 | |
| + Fixed rule | Rule | — | 98.7 | 84.8 | 90.6 | ||
| + PRS | Student | — | 98.8 | 84.9 | 90.7 | ||
| Full framework and teacher reference | |||||||
| Method | PDMS | vs. EAS | Gain retained (%) | Rollouts / trigger | Median latency (ms) |
|---|---|---|---|---|---|
| Selection and repair references | |||||
| EAS | 90.4 | +0.00 | — | 0.00 | — |
| Fixed rule | 90.6 | +0.22 | 28.7 | 1.00 | 23.96 |
| PRS | 90.7 | +0.32 | 41.3 | 1.00 | 24.85 |
| Future-conditioned repair and search | |||||
| FCRS | 91.0 | +0.56 | 73.2 | 1.00 | 25.13 |
Appendix figures & tables4 assets
Supplementary material from the paper’s appendix.
Appendix
Autonomous Driving Planning
Autonomous driving planning selects safe, feasible vehicle actions and trajectories amid traffic, uncertainty, road rules, and changing goals.
See all 426 papers