AirDreamer: Generalist Drone Navigation with World Models
For drone navigation in cluttered, unseen environments, AirDreamer offers a more generalizable approach that outperforms existing methods.
AirDreamer introduces a drone navigation framework combining a world model with reinforcement learning to generalize to unseen environments. It achieves a 5.3% higher navigation success rate than the best baseline in challenging maps and demonstrates effective sim-to-real transfer without tuning.
Navigating a drone in unseen and cluttered environments requires reliable generalization to unseen scene layouts and understanding of environmental structure relative to the robot's capabilities. Previous methods, which assume the same environment configuration, often rely heavily on human-designed perception pipelines and predefined rules to guide the robot toward the target. This process is environment-dependent and generalizes poorly across environments. Inspired by animal navigation behavior, we design a navigation framework that navigates with a reinforcement-learning-based policy on top of a world-model-based environment understanding to overcome these issues. In addition, a sparse reward function without hand-crafted shaping terms is designed to avoid local minima traps and encourage yaw control behaviors. In simulation and on real drones, our method exhibits emergent capabilities for navigating complex, unseen environments and escaping local optima where other methods fail. In challenging maps, it achieves a 5.3% higher navigation success rate than best baseline. Furthermore, the proposed framework achieves effective sim-to-real transfer without any tuning during deployment. The code will be publicly available.