AdaWM selectively finetunes either the dynamics model or the policy of a pretrained world-model driving agent according to which mismatch dominates, improving success rates in CARLA.
The BEV representation can be learnt by using algorithms such as BevFusion Liu et al
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AdaWM: Adaptive World Model based Planning for Autonomous Driving
AdaWM selectively finetunes either the dynamics model or the policy of a pretrained world-model driving agent according to which mismatch dominates, improving success rates in CARLA.