The checkpoint was warm-started from the MomAD planner and trained with the
matched oracle-mode regularized 6-second configuration included in this
repository. It predicts 12 future steps at 0.5-second intervals.
Fresh evaluation used all 6,019 nuScenes validation samples.
1python open_loop/tools/test.py \
2 open_loop/projects/configs/MomAD_small_stage2_MomAD_World_model_6s_v2_oracle_mode_reg02_resume_repro.py \
3 /path/to/momworld_nuscenes_6s_oracle_iter_18752.pth \
4 --out /tmp/momworld_results.pkl \
5 --eval bbox
The nuScenes dataset, generated metadata, anchors, and evaluation outputs are
not included. Follow the repository setup instructions and the nuScenes terms
of use. This is a research checkpoint and should not be used as a standalone
safety-critical driving system.
