mlsanityData to 14 Oct 2026

The Power of Input: Benchmarking Zero-Shot Sim-To-Real Transfer of Reinforcement Learning Control Policies for Quadrotor Control

arXiv 2410.07686 ↗First posted 10 Oct 2024cs.ROcited by 5

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

Abstract (arXiv)

In the last decade, data-driven approaches have become popular choices for quadrotor control, thanks to their ability to facilitate the adaptation to unknown or uncertain flight conditions. Among the different data-driven paradigms, Deep Reinforcement Learning (DRL) is currently one of the most explored. However, the design of DRL agents for Micro Aerial Vehicles (MAVs) remains an open challenge. While some works have studied the output configuration of these agents (i.e., what kind of control to compute), there is no general consensus on the type of input data these approaches should employ. Multiple works simply provide the DRL agent with full state information, without questioning if this might be redundant and unnecessarily complicate the learning process, or pose superfluous constraints on the availability of such information in real platforms. In this work, we provide an in-depth benchmark analysis of different configurations of the observation space. We optimize multiple DRL agents in simulated environments with different input choices and study their robustness and their sim-to-real transfer capabilities with zero-shot adaptation. We believe that the outcomes and discussions presented in this work supported by extensive experimental results could be an important milestone in guiding future research on the development of DRL agents for aerial robot tasks.

Key facts. Cited by 5 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 13 of its 32 references that are in the map. First posted on arXiv 10 Oct 2024.

Builds on

13 of 32 references.

References · 13

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2017Asymmetric Actor Critic for Image-Based Robot Learningcited by 238
  3. 2020Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Criticscited by 165
  4. 2017Control of a Quadrotor with Reinforcement Learningcited by 92
  5. 2022A Benchmark Comparison of Learned Control Policies for Agile Quadrotor Flightcited by 47
  6. 2022Real-time Neural-MPC: Deep Learning Model Predictive Control for Quadrotors and Agile Robotic Platformscited by 41
  7. 2018PAMPC: Perception-Aware Model Predictive Control for Quadrotorscited by 28
  8. 2022Learning Minimum-Time Flight in Cluttered Environmentscited by 16
  9. 2022Aggressive Quadrotor Flight Using Curiosity-Driven Reinforcement Learningcited by 8
  10. 2022Visual Attention Prediction Improves Performance of Autonomous Drone Racing Agentscited by 7
  11. 2020A Comprehensive Survey of Control Strategies for Autonomous Quadrotorscited by 2
  12. 2022Learning Model Predictive Control for Quadrotorscited by 2
1 more
  1. 2023Exploring Deep Reinforcement Learning for Robust Target Tracking using Micro Aerial Vehiclescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 1.

5 papers.

  1. 2024What Matters in Learning A Zero-Shot Sim-to-Real RL Policy for Quadrotor Control? A Comprehensive Studycited by 11
  2. 2025Leveling the Playing Field: Carefully Comparing Classical and Learned Controllers for Quadrotor Trajectory Trackingcited by 6
  3. 2025Curriculum-based Sample Efficient Reinforcement Learning for Robust Stabilization of a Quadrotorcited by 1
  4. 2025RL-based Control of UAS Subject to Significant Disturbancecited by 0
  5. 2026Online Reinforcement Learning for Safe Gain Scheduling in Nonlinear Quadrotor Controlcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Task-Oriented Flying: Framework, Infrastructure, and Principles
  2. 2025Dynamics-Invariant Quadrotor Control using Scale-Aware Deep Reinforcement Learning
  3. 2026Adaptive Outer-Loop Control of Quadrotors via Reinforcement Learning
  4. 2026Physics-Aware End-to-End Deep Reinforcement Learning for Quadcopter Control with Actuator Dynamics
  5. 2025RAPTOR: A Foundation Policy for Quadrotor Control
  6. 2024Deep Reinforcement Learning for Sim-to-Real Policy Transfer of VTOL-UAVs Offshore Docking Operations
  7. 2025Hovering Flight of Soft-Actuated Insect-Scale Micro Aerial Vehicles using Deep Reinforcement Learning
  8. 2024A Learning-based Quadcopter Controller with Extreme Adaptation