mlsanityData to 14 Oct 2026

Reinforcement Learning for Collision-free Flight Exploiting Deep Collision Encoding

arXiv 2402.03947 ↗First posted 6 Feb 2024cs.ROcited by 13

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

Abstract (arXiv)

This work contributes a novel deep navigation policy that enables collision-free flight of aerial robots based on a modular approach exploiting deep collision encoding and reinforcement learning. The proposed solution builds upon a deep collision encoder that is trained on both simulated and real depth images using supervised learning such that it compresses the high-dimensional depth data to a low-dimensional latent space encoding collision information while accounting for the robot size. This compressed encoding is combined with an estimate of the robot's odometry and the desired target location to train a deep reinforcement learning navigation policy that offers low-latency computation and robust sim2real performance. A set of simulation and experimental studies in diverse environments are conducted and demonstrate the efficiency of the emerged behavior and its resilience in real-life deployments.

Key facts. Cited by 13 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 33 of its 48 references that are in the map. First posted on arXiv 6 Feb 2024.

Builds on

33 of 48 references.

References · 33

  1. 2016Tutorial on Variational Autoencoderscited by 409
  2. 2021End-to-end Interpretable Neural Motion Plannercited by 242
  3. 2021Learning High-Speed Flight in the Wildcited by 128
  4. 2023Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learningcited by 111
  5. 2020BADGR: An Autonomous Self-Supervised Learning-Based Navigation Systemcited by 102
  6. 2020Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learningcited by 93
  7. 2020Flightmare: A Flexible Quadrotor Simulatorcited by 84
  8. 2019Deep Drone Racing: From Simulation to Reality with Domain Randomizationcited by 76
  9. 2020Deep Drone Acrobaticscited by 75
  10. 2019Motion Planning Networks: Bridging the Gap Between Learning-based and Classical Motion Plannerscited by 66
  11. 2022ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hintscited by 58
  12. 2018Robot Motion Planning in Learned Latent Spacescited by 42
21 more
  1. 2017Learning to Fly by Crashingcited by 41
  2. 2021Learning a State Representation and Navigation in Cluttered and Dynamic Environmentscited by 41
  3. 2019Long-Range Indoor Navigation with PRM-RLcited by 31
  4. 2020AlphaPilot: Autonomous Drone Racingcited by 30
  5. 2022Locomotion Policy Guided Traversability Learning using Volumetric Representations of Complex Environmentscited by 28
  6. 2022How Does It Feel? Self-Supervised Costmap Learning for Off-Road Vehicle Traversabilitycited by 27
  7. 2020LaND: Learning to Navigate from Disengagementscited by 25
  8. 2018Beauty and the Beast: Optimal Methods Meet Learning for Drone Racingcited by 21
  9. 2020Learning-based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environmentscited by 21
  10. 2022CERBERUS: Autonomous Legged and Aerial Robotic Exploration in the Tunnel and Urban Circuits of the DARPA Subterranean Challengecited by 17
  11. 2020NavRep: Unsupervised Representations for Reinforcement Learning of Robot Navigation in Dynamic Human Environmentscited by 15
  12. 2022Team CERBERUS Wins the DARPA Subterranean Challenge: Technical Overview and Lessons Learnedcited by 14
  13. 2020Visual Navigation Among Humans with Optimal Control as a Supervisorcited by 12
  14. 2022Motion Primitives-based Navigation Planning using Deep Collision Predictioncited by 11
  15. 2023Aerial Gym -- Isaac Gym Simulator for Aerial Robotscited by 11
  16. 2022Present and Future of SLAM in Extreme Underground Environmentscited by 10
  17. 2021The Artificial Intelligence behind the winning entry to the 2019 AI Robotic Racing Competitioncited by 8
  18. 2021Double Critic Deep Reinforcement Learning for Mapless 3D Navigation of Unmanned Aerial Vehiclescited by 8
  19. 2023Semantically-enhanced Deep Collision Prediction for Autonomous Navigation using Aerial Robotscited by 7
  20. 2023Task-driven Compression for Collision Encoding based on Depth Imagescited by 7
  21. 2019Nuclear Environments Inspection with Micro Aerial Vehicles: Algorithms and Experimentscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 7.

13 papers.

Sort:

By area:

  1. 2025Flying on Point Clouds with Reinforcement Learningcited by 7
  2. 2025RAPID: Robust and Agile Planner Using Inverse Reinforcement Learning for Vision-Based Drone Navigationcited by 6
  3. 2026Reinforcement Learning for Active Perception in Autonomous Navigationcited by 4
  4. 2024Learning Long-Horizon Predictions for Quadrotor Dynamicscited by 1
  5. 2025Towards Task-Oriented Flying: Framework, Infrastructure, and Principlescited by 1
  6. 2025Synthetic vs. Real Training Data for Visual Navigationcited by 1
  7. 2024Non-Prehensile Aerial Manipulation using Model-Based Deep Reinforcement Learningcited by 0
  8. 2026Zero-Shot UAV Navigation in Forests via Relightable 3D Gaussian Splattingcited by 0
  9. 2026Cross-Modal Reinforcement Learning for Navigation with Degraded Depth Measurementscited by 0
  10. 2026CMRL: Collision-Aware and Memory-Enhanced Reinforcement Learning for UAV Navigation in Multi-Scale Obstacle Environmentscited by 0
  11. 2026A Heuristic Approach for Performance Tuning in RL-based Quadrotor Control via Reward Design and Termination Conditionscited by 0
  12. 2026Vision-Guided Outdoor Flight and Obstacle Evasion via Reinforcement Learningcited by 0
1 more
  1. 2026A 360-Degree Vision Dataset for Learning Yaw Control on GPS-Denied Micro-UAVs in Disaster-Response-Relevant Environmentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Learning-Based Dynamic Obstacle Avoidance for a UAV Using Only Three Range Sensors
  2. 2025Mastering Diverse, Unknown, and Cluttered Tracks for Robust Vision-Based Drone Racing
  3. 2024Robust Policy Learning for Multi-UAV Collision Avoidance with Causal Feature Selection ↗
  4. 2024Dual Agent Learning Based Aerial Trajectory Tracking
  5. 2025Collision-Aware Object-Goal Visual Navigation via Two-Stage Deep Reinforcement Learning
  6. 2024Collision Avoidance for Multiple UAVs in Unknown Scenarios with Causal Representation Disentanglement
  7. 2026High-Speed Vision-Based Flight in Clutter with Safety-Shielded Reinforcement Learning
  8. 2025Flying in Highly Dynamic Environments with End-to-end Learning Approach