让无人机通过强化学习自主调整摄像头，边导航边探索未知环境。
Reinforcement Learning for Active Perception in Autonomous Navigation
- 用强化学习统一控制飞行与摄像头，实现边走边看
- 相比固定摄像头，飞行更安全且自发产生探索行为
- 基于体素的信息度量提升感知效率，适合复杂环境导航
本文针对复杂未知环境中自主导航的主动感知挑战，重新审视主动感知基础原理，提出一种端到端强化学习框架。机器人不仅需到达目标并避障，还需主动控制机载摄像头以增强态势感知。策略接收机器人状态、当前深度图以及由短时深度读数历史构建的局部几何表示。为协调无碰撞运动规划与信息驱动的主动摄像控制，我们在导航奖励中引入基于体素的信息度量。这使空中机器人学会在目标导向运动与探索性感知间取得平衡。大量实验表明，该策略相比固定非动作相机基线，实现了更安全的飞行，并自然诱发内在探索行为。
原文摘要 · Abstract (English)
This paper addresses the challenge of active perception within autonomous navigation in complex, unknown environments. Revisiting the foundational principles of active perception, we introduce an end-to-end reinforcement learning framework in which a robot must not only reach a goal while avoiding obstacles, but also actively control its onboard camera to enhance situational awareness. The policy receives observations comprising the robot state, the current depth frame, and a particularly local geometry representation built from a short history of depth readings. To couple collision-free motion planning with information-driven active camera control, we augment the navigation reward with a voxel-based information metric. This enables an aerial robot to learn a robust policy that balances goal-directed motion with exploratory sensing. Extensive evaluation demonstrates that our strategy achieves safer flight compared to using fixed, non-actuated camera baselines while also inducing intrinsic exploratory behaviors.
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。