mlsanityData to 14 Oct 2026

Dynamics-Invariant Quadrotor Control using Scale-Aware Deep Reinforcement Learning

arXiv 2503.09622 ↗First posted 9 Mar 2025eess.SY cs.RO cs.SYcited by 0

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

Abstract (arXiv)

Due to dynamic variations such as changing payload, aerodynamic disturbances, and varying platforms, a robust solution for quadrotor trajectory tracking remains challenging. To address these challenges, we present a deep reinforcement learning (DRL) framework that achieves physical dynamics invariance by directly optimizing force/torque inputs, eliminating the need for traditional intermediate control layers. Our architecture integrates a temporal trajectory encoder, which processes finite-horizon reference positions/velocities, with a latent dynamics encoder trained on historical state-action pairs to model platform-specific characteristics. Additionally, we introduce scale-aware dynamics randomization parameterized by the quadrotor's arm length, enabling our approach to maintain stability across drones spanning from 30g to 2.1kg and outperform other DRL baselines by 85% in tracking accuracy. Extensive real-world validation of our approach on the Crazyflie 2.1 quadrotor, encompassing over 200 flights, demonstrates robust adaptation to wind, ground effects, and swinging payloads while achieving less than 0.05m RMSE at speeds up to 2.0 m/s. This work introduces a universal quadrotor control paradigm that compensates for dynamic discrepancies across varied conditions and scales, paving the way for more resilient aerial systems.

Key facts. No citing papers in the map yet (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 20 of its 25 references that are in the map. First posted on arXiv 9 Mar 2025.

Builds on

20 of 25 references.

References · 20

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018DeepMind Control Suitecited by 956
  3. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 508
  4. 2017Control of a Quadrotor with Reinforcement Learningcited by 92
  5. 2022Neural-Fly Enables Rapid Learning for Agile Flight in Strong Windscited by 85
  6. 2019Deep Drone Racing: From Simulation to Reality with Domain Randomizationcited by 76
  7. 2018Unmanned Aerial Vehicles: A Survey on Civil Applications and Key Research Challengescited by 54
  8. 2022A Benchmark Comparison of Learned Control Policies for Agile Quadrotor Flightcited by 47
  9. 2019Sim-to-(Multi)-Real: Transfer of Low-Level Robust Control Policies to Multiple Quadrotorscited by 45
  10. 2021Data-Driven MPC for Quadrotorscited by 35
  11. 2023Learning to Fly in Secondscited by 31
  12. 2022Learning a Single Near-hover Position Controller for Vastly Different Quadcopterscited by 21
8 more
  1. 2023Actor-Critic Model Predictive Control: Differentiable Optimization meets Reinforcement Learning for Agile Flightcited by 19
  2. 2022Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Trackingcited by 18
  3. 2024A Learning-based Quadcopter Controller with Extreme Adaptationcited by 17
  4. 2023DATT: Deep Adaptive Trajectory Tracking for Quadrotor Controlcited by 16
  5. 2017Linear Matrix Inequalities for Physically-Consistent Inertial Parameter Identification: A Statistical Perspective on the Mass Distributioncited by 12
  6. 2021Demonstration-Efficient Guided Policy Search via Imitation of Robust Tube MPCcited by 11
  7. 2024What Matters in Learning A Zero-Shot Sim-to-Real RL Policy for Quadrotor Control? A Comprehensive Studycited by 11
  8. 2018Adaptive Model Predictive Control for High-Accuracy Trajectory Tracking in Changing Conditionscited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Adaptive Outer-Loop Control of Quadrotors via Reinforcement Learning
  2. 2026Physics-Aware End-to-End Deep Reinforcement Learning for Quadcopter Control with Actuator Dynamics
  3. 2025Reactive Aerobatic Flight via Reinforcement Learning
  4. 2026GustPilot: A Hierarchical DRL-INDI Framework for Wind-Resilient Quadrotor Navigation ↗
  5. 2025Leveling the Playing Field: Carefully Comparing Classical and Learned Controllers for Quadrotor Trajectory Tracking
  6. 2024DroneDiffusion: Robust Quadrotor Dynamics Learning with Diffusion Models
  7. 2025Towards Task-Oriented Flying: Framework, Infrastructure, and Principles
  8. 2025RAPTOR: A Foundation Policy for Quadrotor Control