The paper reports that a VLM-guided end-to-end driving system reduces average collision rates on nuScenes by 31.82% compared with its VAD baseline, while also generating text explanations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VLAD: A VLM-Augmented Autonomous Driving Framework with Hierarchical Planning and Interpretable Decision Process
The paper reports that a VLM-guided end-to-end driving system reduces average collision rates on nuScenes by 31.82% compared with its VAD baseline, while also generating text explanations.