Skip to main content
Search

# Trajectory Preference Scoring

1 related articles

Subscribe to updates
  1. arXiv

    Takeover logs aren't copied verbatim: shifting human corrections lifts closed-loop success from 70.87% to 81.60%

    Real fleet takeover logs are imperfect: drivers may intervene too late or unnecessarily, so direct imitation can teach a model delayed reactions or needless corrections. An offline post-training method shifts recorded human corrections earlier by several time offsets and perturbs the deployed model's multimodal plans to build trajectory candidates, then ranks them with a scene-conditioned scorer trained on expert trajectory matching and unpaired preference signals from takeover logs. On a closed-loop benchmark of 596 real challenging scenarios reconstructed with 4D Gaussian splatting, the method reaches 81.60% overall success, versus 70.87% for the deployed model and 75.30% for direct imitation learning.

You’re all caught up