Loading
Life sciences · Preprint
arXiv · September 3, 2026
Early or partial results. Treat as a signal, not a conclusion.
This preprint describes a novel low-cost experimental platform for end-to-end autonomous driving research on miniature vehicles, combining simulation and real-world testing. The authors demonstrate that a command-conditioned imitation-learning policy trained on synthetic data with sim-to-real translation completes all four track routes in closed loop, whereas versions trained on real data alone do not, but the work is preliminary, unrefereed, and confined to a controlled miniature-vehicle setting.
Single-arm experimental platform demonstration with simulation and real-world validation. Miniature Ackermann vehicles tested on a printed urban track in controlled experimental settings. Intervention: Command-conditioned behavior cloning neural policy trained on real demonstrations, synthetic data, or combinations thereof, with optional sim-to-real image translation. Compared with: Multiple policy configurations compared: compact baseline, same network trained only on real data, higher-capacity network trained on synthetic data with real demonstrations.
Real closed-loop mean cross-track error of 6.1 cm, approaching human demonstration performance of 4.7 cm Camera field of view strongly affects simulated performance, reducing mean cross-track error from 35.6 to 3.3 cm when widened from 58 to 120 degrees Hybrid policy trained on synthetic data with sim-to-real translation was the only configuration to complete all four track routes in closed loop
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
This is an unvalidated technical platform paper demonstrating proof-of-concept for miniature autonomous vehicle control using imitation learning, without peer review, clinical outcomes, or external validation.
As stated by the source record.
Quoted from the source exactly as published.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
This paper presents a low-cost, open experimental platform for research in end-to-end autonomous driving with miniature Ackermann vehicles. The platform combines a physical vehicle, a printed urban track, data collection tools, trajectory registration, and a Webots digital twin, enabling controlled experiments that connect simulation-based autonomous-driving methods to real-world execution. As a first baseline, we implement command-conditioned behavior cloning, in which a neural policy receives an on-board camera image and a high-level navigation command and outputs steering and speed. The system is evaluated both on the physical vehicle and in simulation. In real closed-loop experiments, the learned policy follows lanes and executes commanded turns, reaching a mean cross-track error of 6.1 cm with respect to the reference route, close to the 4.7 cm observed in human demonstrations. In the digital twin, camera field of view has a strong effect on performance, reducing the mean cross-track error from 35.6 to 3.3 cm when widened from 58 to 120 degrees. Using the digital twin to generate synthetic driving data and a learned sim-to-real image translator to reduce the appearance gap, we further show that a higher-capacity policy trained on this synthetic data combined with real demonstrations is the only configuration that completes all four track routes in closed loop, whereas the compact baseline and the same network trained on real data alone complete fewer. These results establish the open platform as a practical testbed for sim-to-real studies and provide an initial command-conditioned imitation-learning baseline; we release it to support reproducible research.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.