robotics
Driving Actions Split Motion from Centimeter Corrections
VITAL makes visually derived motion the main action target, then carries the remaining trajectory error in a small residual code.
Summary
VITAL makes visually derived motion the main action target, then carries the remaining trajectory error in a small residual code.
A future image can reveal the shape of a driving maneuver while still missing the exact trajectory needed for control. VITAL separates those scales: a motion scaffold comes from visual dynamics, and a compact residual records the metric error left behind. With one action-denoising step, the authors report 90.8 PDMS on NAVSIM v1 navtest—within 0.13 points of the ten-step result—at 3.29 times the end-to-end inference speed. Its NAVSIM v2 scores require no retraining. These are simulator-benchmark outcomes, not public-road validation.
Why it matters
VITAL makes visually derived motion the main action target, then carries the remaining trajectory error in a small residual code.
Limits and context
- These are simulator-benchmark outcomes, not public-road validation.
Key claims
VITAL makes visually derived motion the main action target, then carries the remaining trajectory error in a small residual code.
Qualification: These are simulator-benchmark outcomes, not public-road validation.
Evidence: source-2026-10-15-006
Sources
- arXiv preprint 2610.20604, original v1arXiv / submitting research authors · primary research
Corrections
: Publication note: This October 15 edition was prepared before its scheduled 9:00 AM America/Detroit reveal, but publication was delayed by a production build failure. The original reporting and image-generation timestamps are preserved.