Uploaded February 2026 | Updated November 2026, 16 minutes ago
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 novel 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.
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 novel 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.
![Aerial View of the CTC UAV Test Site reconstructed dense point cloud
Video accompanying the technical report: K. Alexis, Dataset: Aerial Views of the CTC UAV Test Site in Collsuspina, Spain.
More info: www.kostas-alexis.com - Research - Datasets - Aerial Views of the CTC UAV Test Site in Collsuspina, Spain
[direct URL: http://www.kostas-alexis.com/research/5-datasets/ctc-uav-test-site ] Aerial View of the CTC UAV Test Site reconstructed dense point cloud](https://i.ytimg.com/vi/qEvLfZl2a9Y/mqdefault.jpg)









