mlsanityData to 14 Oct 2026

Reinforcement Learning for Active Perception in Autonomous Navigation

arXiv 2602.01266 ↗First posted 1 Feb 2026cs.ROcited by 4

On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 14 of its 28 references that are in the map. First posted on arXiv 1 Feb 2026.

Builds on

14 of 28 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Quadrotor Navigation using Reinforcement Learning with Privileged Information9 Sep
  2. 2025Semantically-driven Deep Reinforcement Learning for Inspection Path Planning20 May
  3. 2024Reinforcement Learning for Collision-free Flight Exploiting Deep Collision Encoding6 Feb

Other references · 11

  1. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 883
  2. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 429
  3. 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 366
  4. 2016Learning to Navigate in Complex Environmentscited by 198
  5. 2021Learning High-Speed Flight in the Wildcited by 128
  6. 2016Revisiting Active Perceptioncited by 94
  7. 2020Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learningcited by 93
  8. 2024Back to Newton's Laws: Learning Vision-based Agile Flight via Differentiable Physicscited by 45
  9. 2025Aerial Gym Simulator: A Framework for Highly Parallelized Simulation of Aerial Robotscited by 15
  10. 2023Task-driven Compression for Collision Encoding based on Depth Imagescited by 7
  11. 2022Active Perception Applied To Unmanned Aerial Vehicles Through Deep Reinforcement Learningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Fast Human Attention Prediction for Fixation-guided Active Perception in Autonomous Navigationcited by 0
  2. 2026LEAP: Learning Emergent Active Perception for Quadruped Navigationcited by 0
  3. 2026UAVs Meet Embodied Intelligence: Bridging Human Intents and Flying Dynamics Via Harnessing Physical-Digital AI Agentscited by 0
  4. 2026ClearNav: Perception-Aligned Quadrotor Flight Using Differential-Physicscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Learning Perception-Aware Agile Flight in Cluttered Environments
  2. 2025ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning
  3. 2025SIGN: Safety-Aware Image-Goal Navigation for Autonomous Drones via Reinforcement Learning
  4. 2026VLN on the Fly: An Onboard Vision-Language Navigation Stack for Aerial Robots
  5. 2026Vision-Guided Outdoor Flight and Obstacle Evasion via Reinforcement Learning
  6. 2025Agile in the Face of Delay: Asynchronous End-to-End Learning for Real-World Aerial Navigation
  7. 2025Sight Over Site: Perception-Aware Reinforcement Learning for Efficient Robotic Inspection
  8. 2025Apple: Toward General Active Perception via Reinforcement Learning