Measuring What Matters: Scenario-Driven Evaluation for Trajectory Predictors in Autonomous Driving

Longchao Da; David Isele; Hua Wei; Manish Saroya

AAAI 2026technical0 citations

Measuring What Matters: Scenario-Driven Evaluation for Trajectory Predictors in Autonomous Driving

Longchao Da, David Isele, Hua Wei, Manish Saroya

Abstract

Being able to anticipate the motion of surrounding agents is essential for the safe operation of autonomous driving systems in dynamic situations. While various methods have been proposed for trajectory prediction, the current evaluation practices still rely on error-based metrics (e.g., ADE, FDE), which reveal the accuracy from a post-hoc view but ignore the actual effect the predictor brings to the self-driving vehicles (SDVs), especially in complex interactive scenarios: a high-quality predictor not only chases accuracy, but should also captures all possible directions a neighbor agent might move, to support the SDVs

BibTeX

@inproceedings{aaai2026_measuringwhatmat,
  title = {Measuring What Matters: Scenario-Driven Evaluation for Trajectory Predictors in Autonomous Driving},
  author = {Longchao Da and David Isele and Hua Wei and Manish Saroya},
  booktitle = {AAAI 2026},
  year = {2026}
}