mlsanityData to 14 Oct 2026

Learning to Fly in Seconds

arXiv 2311.13081 ↗First posted 22 Nov 2023cs.RO cs.AI cs.LGcited by 31

Not on the map. Why?

Abstract (arXiv)

Learning-based methods, particularly Reinforcement Learning (RL), hold great promise for streamlining deployment, enhancing performance, and achieving generalization in the control of autonomous multirotor aerial vehicles. Deep RL has been able to control complex systems with impressive fidelity and agility in simulation but the simulation-to-reality transfer often brings a hard-to-bridge reality gap. Moreover, RL is commonly plagued by prohibitively long training times. In this work, we propose a novel asymmetric actor-critic-based architecture coupled with a highly reliable RL-based training paradigm for end-to-end quadrotor control. We show how curriculum learning and a highly optimized simulator enhance sample complexity and lead to fast training times. To precisely discuss the challenges related to low-level/end-to-end multirotor control, we also introduce a taxonomy that classifies the existing levels of control abstractions as well as non-linearities and domain parameters. Our framework enables Simulation-to-Reality (Sim2Real) transfer for direct RPM control after only 18 seconds of training on a consumer-grade laptop as well as its deployment on microcontrollers to control a multirotor under real-time guarantees. Finally, our solution exhibits competitive performance in trajectory tracking, as demonstrated through various experimental comparisons with existing state-of-the-art control solutions using a real Crazyflie nano quadrotor. We open source the code including a very fast multirotor dynamics simulator that can simulate about 5 months of flight per second on a laptop GPU. The fast training times and deployment to a cheap, off-the-shelf quadrotor lower the barriers to entry and help democratize the research and development of these systems.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 29 of its 46 references that are in the map. First posted on arXiv 22 Nov 2023.

Builds on

29 of 46 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2015Continuous control with deep reinforcement learningcited by 3,407
  4. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  5. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  6. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  7. 2019Solving Rubik's Cube with a Robot Handcited by 734
  8. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 672
  9. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 523
  10. 2017Asymmetric Actor Critic for Image-Based Robot Learningcited by 238
  11. 2016CAD2RL: Real Single-Image Flight without a Single Real Imagecited by 233
  12. 2017Control of a Quadrotor with Reinforcement Learningcited by 92
17 more
  1. 2020Flightmare: A Flexible Quadrotor Simulatorcited by 84
  2. 2021Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Controlcited by 77
  3. 2020Deep Drone Acrobaticscited by 75
  4. 2021Autonomous Drone Racing with Deep Reinforcement Learningcited by 60
  5. 2022A Benchmark Comparison of Learned Control Policies for Agile Quadrotor Flightcited by 47
  6. 2019Sim-to-(Multi)-Real: Transfer of Low-Level Robust Control Policies to Multiple Quadrotorscited by 45
  7. 2019Low Level Control of a Quadrotor with Deep Model-Based Reinforcement Learningcited by 44
  8. 2020Model-Based Meta-Reinforcement Learning for Flight with Suspended Payloadscited by 30
  9. 2022Learning a Single Near-hover Position Controller for Vastly Different Quadcopterscited by 21
  10. 2020Learning to Fly via Deep Model-Based Reinforcement Learningcited by 20
  11. 2021Inclined Quadrotor Landing using Deep Reinforcement Learningcited by 7
  12. 2019Flight Controller Synthesis Via Deep Reinforcement Learningcited by 5
  13. 2017Autonomous Quadrotor Landing using Deep Reinforcement Learningcited by 4
  14. 2019Flying through a narrow gap using neural network: an end-to-end planning and control approachcited by 4
  15. 2022Using Simulation Optimization to Improve Zero-shot Policy Transfer of Quadrotorscited by 4
  16. 2023RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Controlcited by 4
  17. 2022RotorTM: A Flexible Simulator for Aerial Transportation and Manipulationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 8; 2025: 13; 2026: 10.

31 papers.

Sort:

By area:

  1. 2024Demonstrating Agile Flight from Pixels without State Estimationcited by 31
  2. 2024Multi-Task Reinforcement Learning for Quadrotorscited by 20
  3. 2024Learning Quadrotor Control From Visual Features Using Differentiable Simulationcited by 19
  4. 2025Dream to Fly: Model-Based Reinforcement Learning for Vision-Based Drone Flightcited by 15
  5. 2024What Matters in Learning A Zero-Shot Sim-to-Real RL Policy for Quadrotor Control? A Comprehensive Studycited by 11
  6. 2025RAPTOR: A Foundation Policy for Quadrotor Controlcited by 8
  7. 2025One Net to Rule Them All: Domain Randomization in Quadcopter Racing Across Different Platformscited by 7
  8. 2024Skill Transfer and Discovery for Sim-to-Real Learning: A Representation-Based Viewpointcited by 6
  9. 2024Learning to Swim: Reinforcement Learning for 6-DOF Control of Thruster-driven Autonomous Underwater Vehiclescited by 6
  10. 2025Leveling the Playing Field: Carefully Comparing Classical and Learned Controllers for Quadrotor Trajectory Trackingcited by 6
  11. 2024ProxFly: Robust Control for Close Proximity Quadcopter Flight via Residual Reinforcement Learningcited by 4
  12. 2025Decentralized Aerial Manipulation of a Cable-Suspended Load using Multi-Agent Reinforcement Learningcited by 4
19 more
  1. 2025RoVerFly: Robust and Versatile Implicit Hybrid Control of Quadrotor-Payload Systemscited by 4
  2. 2025Equivariant Neural Networks for General Linear Symmetries on Lie Algebrascited by 4
  3. 2025Equivariant Reinforcement Learning Frameworks for Quadrotor Low-Level Controlcited by 2
  4. 2024Deep Reinforcement Learning-based Quadcopter Controller: A Practical Approach and Experimentscited by 1
  5. 2025Curriculum-based Sample Efficient Reinforcement Learning for Robust Stabilization of a Quadrotorcited by 1
  6. 2025Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networkscited by 1
  7. 2026Efficient Knowledge Transfer for Jump-Starting Control Policy Learning of Multirotors through Physics-Aware Neural Architecturescited by 1
  8. 2026Crazyflow: An Accurate, GPU-Accelerated, Differentiable Drone Simulator in JAXcited by 1
  9. 2025Maintaining Plasticity in Reinforcement Learning: A Cost-Aware Framework for Aerial Robot Control in Non-stationary Environmentscited by 0
  10. 2025Dynamics-Invariant Quadrotor Control using Scale-Aware Deep Reinforcement Learningcited by 0
  11. 2025Olfactory Inertial Odometry: Sensor Calibration and Drift Compensationcited by 0
  12. 2026MAVEN: A Meta-Reinforcement Learning Framework for Varying-Dynamics Expertise in Agile Quadrotor Maneuverscited by 0
  13. 2026Aerial Inspection Behaviors via RL-based Quadrotor Control for Under-canopy Forest Environmentscited by 0
  14. 2026MinNav: Minimalist Navigation Using Optical Flow For Active Tiny Aerial Robotscited by 0
  15. 2026Embodiment-conditioned Generalist Control for Multirotor Aerial Robotscited by 0
  16. 2026FlashNav: Training Deployable Robot Navigation Policies in Secondscited by 0
  17. 2026Agile Fall Recovery for Quadrotors with Bidirectional Thrust via Reinforcement Learningcited by 0
  18. 2026A Single Diffusion-Policy Controller for Multi-Task Block Pushing with Zero-Shot Sim-to-Real Transfercited by 0
  19. 2026GzDRL: Reproducible and Scalable Deep Reinforcement Learning with Gazebocited by 0