Control-ITRA conditions a learned driving behavior model on waypoints and target speeds, using a sampling-based training scheme, and shows better condition satisfaction and benchmark reward than RL baselines.
Real time trajectory prediction for collision risk estimation between vehicles
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Control-ITRA: Controlling the Behavior of a Driving Model
Control-ITRA conditions a learned driving behavior model on waypoints and target speeds, using a sampling-based training scheme, and shows better condition satisfaction and benchmark reward than RL baselines.