NAVSIM
A benchmark for evaluating autonomous driving planning algorithms, comprising test subsets such as navtest and navhard. It uses composite scoring metrics including PDMS and EPDMS to assess planning quality, covering dimensions such as collision avoidance, drivable-area compliance, comfort and progress.
Timeline (last 90 days)
PDMS (Predictive Driver Model Score) is a composite scoring metric used in the NAVSIM benchmark to measure planning quality, covering dimensions such as collision avoidance, drivable-area compliance, comfort and progress, where a higher value indicates safer planning that is closer to human driving behavior.
navhard is the more difficult test subset in NAVSIM, specifically containing interaction-dense, higher-risk scenarios, and the same model's score on navhard is usually significantly lower than on navtest.
All Facts (2)
PDMS (Predictive Driver Model Score) is a composite scoring metric used in the NAVSIM benchmark to measure planning quality, covering dimensions such as collision avoidance, drivable-area compliance, comfort and progress, where a higher value indicates safer planning that is closer to human driving behavior.
50%Unverifiednavhard is the more difficult test subset in NAVSIM, specifically containing interaction-dense, higher-risk scenarios, and the same model's score on navhard is usually significantly lower than on navtest.
50%