robotics
A Wider Tiny-Car Camera Cut Error by Thirty-Two Centimeters
An open Ackermann testbed links a physical model car, printed streets, data tools and a Webots twin for repeatable sim-to-real work.
Summary
An open Ackermann testbed links a physical model car, printed streets, data tools and a Webots twin for repeatable sim-to-real work.
The command-conditioned policy consumes a camera view and navigation instruction, then outputs steering and speed. On the physical vehicle it reached 6.1-centimeter mean cross-track error versus 4.7 centimeters in human demonstrations. In the digital twin, widening the camera field of view from 58 to 120 degrees reduced error from 35.6 to 3.3 centimeters; only the larger policy trained on synthetic plus real data completed all four closed-loop routes. The authors released the platform as a research baseline, not a road-ready driving system.
Why it matters
An open Ackermann testbed links a physical model car, printed streets, data tools and a Webots twin for repeatable sim-to-real work.
Limits and context
- In the digital twin, widening the camera field of view from 58 to 120 degrees reduced error from 35.6 to 3.3 centimeters; only the larger policy trained on synthetic plus real data completed all four closed-loop routes.
- The authors released the platform as a research baseline, not a road-ready driving system.
Key claims
An open Ackermann testbed links a physical model car, printed streets, data tools and a Webots twin for repeatable sim-to-real work.
Qualification: In the digital twin, widening the camera field of view from 58 to 120 degrees reduced error from 35.6 to 3.3 centimeters; only the larger policy trained on synthetic plus real data completed all four closed-loop routes.
Evidence: source-2026-09-04-010
Sources
- arXiv preprint 2609.04147arXiv · primary research
Corrections
No corrections have been recorded for this story.