VLM-based system constructs per-pixel motorcycle risk maps from semantic and physical hazard attributes, then uses a sampling-based planner to minimize exposure in CARLA simulation.
Insight: Enhancing autonomous driving safety through vision-language models on context- aware hazard detection and edge case evaluation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
VLM-Based Advanced Rider Assistance System for Motorcycle Safety
VLM-based system constructs per-pixel motorcycle risk maps from semantic and physical hazard attributes, then uses a sampling-based planner to minimize exposure in CARLA simulation.