Metraipolis › archive › dc_8e37795d6780
TerraTransfer++: Demonstration-Free End-to-End Planner — arXiv:2610.30319
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.30319
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-23T15:14:50.465Z
- SHA-256 of the archived text
cd934cfe7b91707bfd64115688046d1185eaa20162dc22394ac9bcf9ee772f40- Stable URL of this page
https://metraipolis.com/documento/dc_8e37795d6780
How to cite
TerraTransfer++: Demonstration-Free End-to-End Planner — arXiv:2610.30319 — arXiv (en), https://arxiv.org/abs/2610.30319 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8e37795d6780 (Metraipolis archive dc_8e37795d6780, sha256 cd934cfe7b91707bfd64115688046d1185eaa20162dc22394ac9bcf9ee772f40)
BibTeX
@misc{dc8e37795d6780,
title = {TerraTransfer++: Demonstration-Free End-to-End Planner — arXiv:2610.30319},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.30319},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8e37795d6780; sha256 cd934cfe7b91707bfd64115688046d1185eaa20162dc22394ac9bcf9ee772f40},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30319. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
End-to-end autonomous driving has achieved state-of-the-art performance on benchmarks and real-world deployments. Its standard training recipe, however, is expensive across all existing paradigms: imitation learning requires fleet-scale driving logs whose behavior distribution only thinly covers the safety-critical tail; closed-loop reinforcement learning in a photorealistic simulator, while offering diverse behaviors, is bottlenecked by sample-efficiency, per-step cost of rendering, and a forward pass through a large vision backbone. Self-play in vectorized simulators changes the economics: at millions of rollout steps per second, one can obtain a state distribution with natural diversity in collisions, near-misses, and recoveries that no driving log contains, and a highly reactive policy emerges from a basic driving-quality reward. Our approach exploits this asymmetry. We pretrain a single policy by self-play, distill its rollouts into a flow-matching trajectory teacher that also plans, and train lightweight adapters on a frozen pretrained vision backbone to reproduce the latent space of either teacher through the action KL divergence, a batch-relational low-rank structural loss, and, for the planner, a trajectory-matching loss. Every target traces back to the self-play policy, so alignment never supervises against a logged trajectory: a paired dataset of (image, scene-state) frames suffices, with no need for the curated expert demonstrations that imitation pretraining is built on. From this one self-play teacher we obtain two end-to-end students: a closed-loop policy that outperforms every published imitation-based end-to-end method on the photorealistic 3D Gaussian splatting closed-loop benchmark HUGSim, and a planner that reaches 59.4 EPDMS on NAVSIM navhard, above every published method including DriveZero-Scale (57.1), and 95.5 PDMS on navtest, without human demonstrations. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.30319 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-23T15:09:08.507Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).