Metraipolis › archive › dc_e9061fa7be40
Closed-Loop Evaluation of Bird's-Eye-View Maps from Cross-View Transformers as Inputs to Behavior-Cloning Policies — arXiv:2609.05783
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.05783
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:12:39.190Z
- SHA-256 of the archived text
95e5543ead8e72bfa2617e7f883b85c074fde3992406175003f70f7fbae886b8- Stable URL of this page
https://metraipolis.com/documento/dc_e9061fa7be40
How to cite
Closed-Loop Evaluation of Bird's-Eye-View Maps from Cross-View Transformers as Inputs to Behavior-Cloning Policies — arXiv:2609.05783 — arXiv (en), https://arxiv.org/abs/2609.05783 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e9061fa7be40 (Metraipolis archive dc_e9061fa7be40, sha256 95e5543ead8e72bfa2617e7f883b85c074fde3992406175003f70f7fbae886b8)
BibTeX
@misc{dce9061fa7be40,
title = {Closed-Loop Evaluation of Bird's-Eye-View Maps from Cross-View Transformers as Inputs to Behavior-Cloning Policies — arXiv:2609.05783},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.05783},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e9061fa7be40; sha256 95e5543ead8e72bfa2617e7f883b85c074fde3992406175003f70f7fbae886b8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05783. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In autonomous driving, Bird's-Eye View (BEV) representations provide a structured, top-down abstraction of the vehicle's surroundings and have become a key input modality for Behavioral Cloning (BC) policies. While ground-truth BEV maps are readily available in simulation, real-world deployment requires replacing them with camera-predicted counterparts - a substitution that introduces perceptual errors whose downstream impact on closed-loop driving performance is not well understood. In this work, we investigate the use of Cross-View Transformer (CVT)-predicted BEV maps as direct policy inputs for a BC agent in the CARLA simulator. We propose a six-channel BEV representation covering road surface, planned route, lane boundaries, vehicles, pedestrians, and traffic lights, and introduce a Kernel Density Estimation (KDE) weighting scheme that rebalances the segmentation loss towards underrepresented driving maneuvers such as curves and intersections. Closed-loop evaluation across two CARLA towns shows that the KDE-weighted model is the only predicted-BEV agent to complete a full episode without infractions, despite not achieving the highest aggregate IoU. This discrepancy reveals that global segmentation metrics are poor proxies for driving performance: what determines navigation success is prediction quality at geometrically critical locations, and the route channel emerges as the primary bottleneck for reliable agent navigation under predicted BEV inputs. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.05783 — 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 2026-10-16T14:49:57.413Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).