TRAP combines trajectory-ranked IRL rewards with variable-horizon prefix sampling and DistilBERT to detect anomalous driving, reaching 0.90 AUC in simulation.
Sensor data based anomaly detection in autonomous vehicles using modified convolutional neural network
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Anomalous Decision Discovery using Inverse Reinforcement Learning
TRAP combines trajectory-ranked IRL rewards with variable-horizon prefix sampling and DistilBERT to detect anomalous driving, reaching 0.90 AUC in simulation.