mlsanityData to 14 Oct 2026

Towards Task-Oriented Flying: Framework, Infrastructure, and Principles

arXiv 2504.15129 ↗First posted 21 Apr 2025cs.RO cs.AI cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Deploying robot learning methods to aerial robots in unstructured environments remains both challenging and promising. While recent advances in deep reinforcement learning (DRL) have enabled end-to-end flight control, the field still lacks systematic design guidelines and a unified infrastructure to support reproducible training and real-world deployment. We present a task-oriented framework for end-to-end DRL in quadrotors that integrates design principles for complex task specification and reveals the interdependencies among simulated task definition, training design principles, and physical deployment. Our framework involves software infrastructure, hardware platforms, and open-source firmware to support a full-stack learning infrastructure and workflow. Extensive empirical results demonstrate robust flight and sim-to-real generalization under real-world disturbances. By reducing the entry barrier for deploying learning-based controllers on aerial robots, our work lays a practical foundation for advancing autonomous flight in dynamic and unstructured environments.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 51 of its 64 references that are in the map. First posted on arXiv 21 Apr 2025.

Builds on

51 of 64 references.

References · 51

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  3. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 214
  4. 2021Learning High-Speed Flight in the Wildcited by 128
  5. 2023Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learningcited by 111
  6. 2017Control of a Quadrotor with Reinforcement Learningcited by 92
  7. 2020Flightmare: A Flexible Quadrotor Simulatorcited by 84
  8. 2021Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Controlcited by 77
  9. 2019Deep Drone Racing: From Simulation to Reality with Domain Randomizationcited by 76
  10. 2021Autonomous Drone Racing with Deep Reinforcement Learningcited by 60
  11. 2020EGO-Planner: An ESDF-free Gradient-based Local Planner for Quadrotorscited by 55
  12. 2022A Benchmark Comparison of Learned Control Policies for Agile Quadrotor Flightcited by 47
38 more
  1. 2024Back to Newton's Laws: Learning Vision-based Agile Flight via Differentiable Physicscited by 45
  2. 2021NeuroBEM: Hybrid Aerodynamic Quadrotor Modelcited by 37
  3. 2023Autonomous Drone Racing: A Surveycited by 35
  4. 2023OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Controlcited by 33
  5. 2020AlphaPilot: Autonomous Drone Racingcited by 30
  6. 2023Agilicious: Open-Source and Open-Hardware Agile Quadrotor for Vision-Based Flightcited by 30
  7. 2018Memory-based Deep Reinforcement Learning for Obstacle Avoidance in UAV with Limited Environment Knowledgecited by 26
  8. 2024NavRL: Learning Safe Flight in Dynamic Environmentscited by 26
  9. 2020RAPTOR: Robust and Perception-aware Trajectory Replanning for Quadrotor Fast Flightcited by 23
  10. 2019FlightGoggles: A Modular Framework for Photorealistic Camera, Exteroceptive Sensor, and Dynamics Simulationcited by 22
  11. 2022Learning a Single Near-hover Position Controller for Vastly Different Quadcopterscited by 21
  12. 2024Learning Quadrotor Control From Visual Features Using Differentiable Simulationcited by 19
  13. 2017Fast, Autonomous Flight in GPS-Denied and Cluttered Environmentscited by 18
  14. 2022Learning Minimum-Time Flight in Cluttered Environmentscited by 16
  15. 2022Learning Deep Sensorimotor Policies for Vision-based Autonomous Drone Racingcited by 15
  16. 2021Autonomous Quadrotor Flight despite Rotor Failure with Onboard Vision Sensors: Frames vs. Eventscited by 14
  17. 2024Whole-Body Control Through Narrow Gaps From Pixels To Actioncited by 14
  18. 2024Reinforcement Learning for Collision-free Flight Exploiting Deep Collision Encodingcited by 13
  19. 2024MAVRL: Learn to Fly in Cluttered Environments with Varying Speedcited by 13
  20. 2022Deep-PANTHER: Learning-Based Perception-Aware Trajectory Planner in Dynamic Environmentscited by 11
  21. 2023Aerial Gym -- Isaac Gym Simulator for Aerial Robotscited by 11
  22. 2023Learning Vision-based Pursuit-Evasion Robot Policiescited by 11
  23. 2024What Matters in Learning A Zero-Shot Sim-to-Real RL Policy for Quadrotor Control? A Comprehensive Studycited by 11
  24. 2021Flying Through a Narrow Gap Using End-to-end Deep Reinforcement Learning Augmented with Curriculum Learning and Sim2Realcited by 10
  25. 2022Bubble Planner: Planning High-speed Smooth Quadrotor Trajectories using Receding Corridorscited by 10
  26. 2022Time-Optimal Online Replanning for Agile Quadrotor Flightcited by 8
  27. 2022Aggressive Quadrotor Flight Using Curiosity-Driven Reinforcement Learningcited by 8
  28. 2022PencilNet: Zero-Shot Sim-to-Real Transfer Learning for Robust Gate Perception in Autonomous Drone Racingcited by 8
  29. 2022Event-based Navigation for Autonomous Drone Racing with Sparse Gated Recurrent Networkcited by 7
  30. 2023A Sim-to-Real Deep Learning-based Framework for Autonomous Nano-drone Racingcited by 7
  31. 2025Flying on Point Clouds with Reinforcement Learningcited by 7
  32. 2024Dashing for the Golden Snitch: Multi-Drone Time-Optimal Motion Planning with Multi-Agent Reinforcement Learningcited by 6
  33. 2024Environment as Policy: Learning to Race in Unseen Trackscited by 6
  34. 2023Path Planning for Air-Ground Robot Considering Modal Switching Point Optimizationcited by 5
  35. 2019Learning a Controller Fusion Network by Online Trajectory Filtering for Vision-based UAV Racingcited by 4
  36. 2019Deep Convolutional Neural Network-Based Autonomous Drone Navigationcited by 4
  37. 2024Rapid Quadrotor Navigation in Diverse Environments using an Onboard Depth Cameracited by 4
  38. 2023LiDAR-based drone navigation with reinforcement learningcited by 2

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025DiffAero: A GPU-Accelerated Differentiable Simulation Framework for Efficient Quadrotor Policy Learningcited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2024Multi-Task Reinforcement Learning for Quadrotors
  2. 2026Physics-Aware End-to-End Deep Reinforcement Learning for Quadcopter Control with Actuator Dynamics
  3. 2024The Power of Input: Benchmarking Zero-Shot Sim-To-Real Transfer of Reinforcement Learning Control Policies for Quadrotor Control
  4. 2025Reactive Aerobatic Flight via Reinforcement Learning
  5. 2025Dynamics-Invariant Quadrotor Control using Scale-Aware Deep Reinforcement Learning
  6. 2025Leveling the Playing Field: Carefully Comparing Classical and Learned Controllers for Quadrotor Trajectory Tracking
  7. 2025LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation
  8. 2026VisFly-Lab: Unified Differentiable Framework for First-Order Reinforcement Learning of Quadrotor Control