STRAP embeds a spatial-temporal risk potential field into a transformer-LSTM trajectory predictor and claims reduced RMSE on NGSIM and HighD, though the risk-scaled loss adds less than 0.01 m improvement in overall average.
Probabilistic vehicle trajectory prediction over occupancy grid map via recurrent neural network,
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.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
STRAP: Spatial-Temporal Risk-Attentive Vehicle Trajectory Prediction for Autonomous Driving
STRAP embeds a spatial-temporal risk potential field into a transformer-LSTM trajectory predictor and claims reduced RMSE on NGSIM and HighD, though the risk-scaled loss adds less than 0.01 m improvement in overall average.