用世界模型+强化学习让无人机在陌生环境中自主导航，无需人工规则设计。
AirDreamer: Generalist Drone Navigation with World Models
- 基于世界模型理解环境，用强化学习策略实现端到端导航。
- 在复杂地图上比最优基线成功率高5.3%，能有效避开局部最优。
- 无需调参即可实现仿真到现实的迁移，适合真实无人机部署。
在未见过且复杂的环境中导航无人机，需要对未知场景布局具备可靠泛化能力，并理解环境结构与机器人能力之间的关系。以往方法假设环境配置一致，常依赖人工设计的感知流程和预设规则引导机器人到达目标，但这类方法具有环境依赖性，跨环境泛化能力差。受动物导航行为启发，我们设计了一种导航框架：在基于世界模型的环境理解基础上，使用强化学习策略进行导航。同时，设计了无手工奖励塑形的稀疏奖励函数，避免陷入局部最优并鼓励航向控制行为。在仿真和真实无人机上，该方法展现出在复杂未知环境中导航及逃离局部最优的涌现能力，于挑战性地图中相比最优基线导航成功率达5.3%提升。此外，所提框架实现了无需部署调参的有效仿真到现实迁移。代码将公开。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。