VLM-UDMC uses a vision-language model to switch safety cost functions in a model predictive controller and a multi-kernel LSTM to predict traffic trajectories, reporting improved urban driving metrics in CARLA and campus demos.
Interactive decision-making with switchable game modes for automated vehicles at intersections,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
VLM-UDMC: VLM-Enhanced Unified Decision-Making and Motion Control for Urban Autonomous Driving
VLM-UDMC uses a vision-language model to switch safety cost functions in a model predictive controller and a multi-kernel LSTM to predict traffic trajectories, reporting improved urban driving metrics in CARLA and campus demos.