Simulator sidecar supervision on road users during training reduces final displacement error in camera-first open-loop waypoint prediction from 1.815 m to 1.223 m on route-disjoint simulation splits.
Think2drive: Efficient reinforce- ment learning by thinking in latent world model for quasi-realistic autonomous driving (in carla-v2)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
baseline 1polarities
baseline 1representative citing papers
MTA-RL predicts 3D driving affordances from multi-modal sensors with a transformer and uses them as the observation space for an RL policy, yielding better route completion and generalization than baselines in CARLA urban scenarios.
citing papers explorer
-
Mind the Privileged-to-Camera Gap: Actor-Centric Sidecar Supervision for Camera-First Open-Loop Waypoint Prediction
Simulator sidecar supervision on road users during training reduces final displacement error in camera-first open-loop waypoint prediction from 1.815 m to 1.223 m on route-disjoint simulation splits.
-
MTA-RL: Robust Urban Driving via Multi-modal Transformer-based 3D Affordances and Reinforcement Learning
MTA-RL predicts 3D driving affordances from multi-modal sensors with a transformer and uses them as the observation space for an RL policy, yielding better route completion and generalization than baselines in CARLA urban scenarios.