Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives
Open paper
Benchmark
Model
Rank
Results
closed-loop-autonomous-driving-on-hugsim
LTFv7
#3
HD-Score: 34.8
RC: 46.2
navsim-on-navsim-v2-navtest
LTFv7
#4
EPDMS: 90.1
navsim-on-openscene
LTFv7
#26
PDMS: 89.7
Rank counts only results with a code link.