Metraipolis › archive › dc_9b00fec666d2
BranchDrive: A Branch-Structured Dataset for Action-Conditioned Driving Prediction — arXiv:2609.27275
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.27275
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:53:27.413Z
- SHA-256 of the archived text
49a5426e8578e5827811c491d8c58758b7837e9dcb8151310d9fb11258594768- Stable URL of this page
https://metraipolis.com/documento/dc_9b00fec666d2
How to cite
BranchDrive: A Branch-Structured Dataset for Action-Conditioned Driving Prediction — arXiv:2609.27275 — arXiv (en), https://arxiv.org/abs/2609.27275 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9b00fec666d2 (Metraipolis archive dc_9b00fec666d2, sha256 49a5426e8578e5827811c491d8c58758b7837e9dcb8151310d9fb11258594768)
BibTeX
@misc{dc9b00fec666d2,
title = {BranchDrive: A Branch-Structured Dataset for Action-Conditioned Driving Prediction — arXiv:2609.27275},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.27275},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9b00fec666d2; sha256 49a5426e8578e5827811c491d8c58758b7837e9dcb8151310d9fb11258594768},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27275. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Most autonomous-driving datasets record only the action executed by a behavior policy and the single future that followed, providing limited supervision for comparing alternative ego decisions. We introduce BranchDrive, a branch-structured CARLA dataset and benchmark that pairs one canonical pre-decision history with one nominal expert future and twelve physically executed intervention futures spanning acceleration, braking, and left- and right-steering policies at three magnitudes. Each intervention lasts 2.5 s and is followed by expert recovery. Following control-compliance, modality-completeness, replay-fidelity, and action-leakage audits, the frozen benchmark contains 606 independent branch groups and 7,878 associated trajectories. We evaluate prediction of six continuous short-horizon outcomes and a ten-step ego trajectory using action-only, history-only, structured, visual, multimodal, and privileged bird's-eye-view models. On the held-out test split, the structured history-and-action model achieves a macro normalized mean absolute error of 0.5036 and an average displacement error of 2.2042 m, significantly outperforming both restricted baselines. In full-information offline evaluation, its outcome-derived selector increases balanced policy value from 0.5364 to 0.5704 and reduces normalized regret from 0.2674 to 0.1495 relative to the frozen action prior. However, a validation-calibrated minimum-separation guard rejects every intervention, showing that conservative execution remains unresolved. BranchDrive therefore supports action-conditioned short-horizon prediction and fixed-bank offline decision evaluation, but does not establish exact causal effects, binary safety prediction, or closed-loop safety improvement. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.27275 — 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 2026-10-08T12:21:19.453Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).