arXiv · 2611.19922
Lao Siji: Adapting openpilot to Closed-Loop End-to-End Driving in Neural Reconstruction
Abstract
We present Lao Siji, an end-to-end driving policy that ranks third in the 2026 NVIDIA AlpaSim E2E Driving Challenge, ahead of most entries built on foundation models. Instead of training from scratch on a general-purpose vision backbone, we adapt openpilot, an open-source L2 production model. We freeze its vision encoder and fine-tune the policy layers with an ego-state adapter and a route memory. On closed-loop rollouts in neural-reconstructed scenes, we supervise the policy with a privileged map teacher for lateral self-correction and a body-extent loss for road and obstacle clearance, while distilling the base model's remaining outputs to retain car following. Ablations show that self-correction samples carry the gain, while the clearance loss substitutes for them where no teacher exists. Longitudinal safety instead rests on the base model's lead-vehicle estimate behind a rule-based speed layer. Longer training, imitating human logs, and human-log speed targets yield either no measurable gain or adverse effects. Without further training, Lao Siji also places among the leaders on HUGSIM and Odyssey. The final training takes only one GPU-hour and shifts the weights by 3.9% from the shipped model. Code will be released after review.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Chengzhi Gao, Yongzhi Liu, Jinchang Xu, Weichao Zhuang, Guodong Yin. 2026-11-15. Lao Siji: Adapting openpilot to Closed-Loop End-to-End Driving in Neural Reconstruction. https://searcharxiv.com/abs/2611.19922
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.