MAD learns recurrent latent dynamics to reconstruct robocentric occupancy and visibility grids, yielding higher success rates and faster flight than vision-only baselines in simulation and real-world quadrotor experiments.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.RO 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Robustness of world models during cross-environment SSL pretraining predicts sim-to-real transfer success for quadrotor navigation, with discrete latent size and training sequence length as dominant factors.
AirDreamer combines world-model-based environment understanding with an RL policy and sparse rewards to navigate unseen environments, achieving 5.3% higher success than baselines and effective sim-to-real transfer without tuning.
citing papers explorer
-
MAD: Mapping-Aware World Models for Agile Quadrotor Flight
MAD learns recurrent latent dynamics to reconstruct robocentric occupancy and visibility grids, yielding higher success rates and faster flight than vision-only baselines in simulation and real-world quadrotor experiments.
-
Generalization of World Models under Environmental Variability for Vision-based Quadrotor Navigation
Robustness of world models during cross-environment SSL pretraining predicts sim-to-real transfer success for quadrotor navigation, with discrete latent size and training sequence length as dominant factors.
-
AirDreamer: Generalist Drone Navigation with World Models
AirDreamer combines world-model-based environment understanding with an RL policy and sparse rewards to navigate unseen environments, achieving 5.3% higher success than baselines and effective sim-to-real transfer without tuning.