Actor-blind probes outrank human replay and PDM-Closed on NAVSIM's full navtest split when a dependency-sensitive velocity refit diverges and reference-conditioned forgiveness turns shared failures into passes.
In: Confer- ence on Robot Learning (CoRL)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When Shared Rollouts Fail in Defensive Driving Evaluation: A NAVSIM Score Basis Audit
Actor-blind probes outrank human replay and PDM-Closed on NAVSIM's full navtest split when a dependency-sensitive velocity refit diverges and reference-conditioned forgiveness turns shared failures into passes.