A vision-language model classifies road surface and visibility conditions from front-camera images, parametrizing a context-adaptive safety envelope that couples braking and steering through a shared friction budget, achieving 100% trial success in CARLA simulation across adverse conditions.
Systems & Control Letters 196, 106021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VLM-CASE: Vision-Language Model Enabled Context-Adaptive Safety Envelopes for Anticipatory Safe Autonomous Driving
A vision-language model classifies road surface and visibility conditions from front-camera images, parametrizing a context-adaptive safety envelope that couples braking and steering through a shared friction budget, achieving 100% trial success in CARLA simulation across adverse conditions.