LLM-generated semantic descriptions of driving behaviors are encoded and used as privileged information exclusively during SVM+ training to improve alignment with expert driving style recognition while inference uses only sensor data.
The highd dataset: A drone dataset of naturalistic vehicle trajectories on german highways for validation of highly automated driving systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Driving Style Recognition Like an Expert Using Semantic Privileged Information from Large Language Models
LLM-generated semantic descriptions of driving behaviors are encoded and used as privileged information exclusively during SVM+ training to improve alignment with expert driving style recognition while inference uses only sensor data.