A DDQN-based V2X scheduler using a label-free, semantics-aware reward selects which collaborator's BEV features to transmit and outperforms simple baselines in V2X-Sim simulations.
Collaborative perception in autonomous driving: Methods, datasets, and challenges,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep Reinforcement Learning-Based User Scheduling for Collaborative Perception
A DDQN-based V2X scheduler using a label-free, semantics-aware reward selects which collaborator's BEV features to transmit and outperforms simple baselines in V2X-Sim simulations.