mlsanityData to 14 Oct 2026

Low Level Control of a Quadrotor with Deep Model-Based Reinforcement Learning

arXiv 1901.03737 ↗First posted 11 Jan 2019cs.RO cs.LGcited by 44

Not on the map. Why?

Abstract (arXiv)

Designing effective low-level robot controllers often entail platform-specific implementations that require manual heuristic parameter tuning, significant system knowledge, or long design times. With the rising number of robotic and mechatronic systems deployed across areas ranging from industrial automation to intelligent toys, the need for a general approach to generating low-level controllers is increasing. To address the challenge of rapidly generating low-level controllers, we argue for using model-based reinforcement learning (MBRL) trained on relatively small amounts of automatically generated (i.e., without system simulation) data. In this paper, we explore the capabilities of MBRL on a Crazyflie centimeter-scale quadrotor with rapid dynamics to predict and control at <50Hz. To our knowledge, this is the first use of MBRL for controlled hover of a quadrotor using only on-board sensors, direct motor input signals, and no initial dynamics knowledge. Our controller leverages rapid simulation of a neural network forward dynamics model on a GPU-enabled base station, which then transmits the best current action to the quadrotor firmware via radio. In our experiments, the quadrotor achieved hovering capability of up to 6 seconds with 3 minutes of experimental training data.

Key facts. Cited by 44 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 11; 2023: 6; 2024: 4; 2025: 6; 2026: 6.

44 papers.

Sort:

By area:

  1. 2023Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learningcited by 111
  2. 2022Investigating Compounding Prediction Errors in Learned Dynamics Modelscited by 47
  3. 2021MBRL-Lib: A Modular Library for Model-based Reinforcement Learningcited by 42
  4. 2022Real-time Neural-MPC: Deep Learning Model Predictive Control for Quadrotors and Agile Robotic Platformscited by 41
  5. 2023OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Controlcited by 33
  6. 2023Learning to Fly in Secondscited by 31
  7. 2024Demonstrating Agile Flight from Pixels without State Estimationcited by 31
  8. 2021KNODE-MPC: A Knowledge-based Data-driven Predictive Control Framework for Aerial Robotscited by 26
  9. 2022The Challenges of Exploration for Offline Reinforcement Learningcited by 26
  10. 2025Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classificationcited by 26
  11. 2021Learning Dynamics Models for Model Predictive Agentscited by 22
  12. 2022Learning a Single Near-hover Position Controller for Vastly Different Quadcopterscited by 21
32 more
  1. 2024Multi-Task Reinforcement Learning for Quadrotorscited by 20
  2. 2022DHRL: A Graph-Based Approach for Long-Horizon and Sparse Hierarchical Reinforcement Learningcited by 19
  3. 2022Online Dynamics Learning for Predictive Control with an Application to Aerial Robotscited by 17
  4. 2025Dream to Fly: Model-Based Reinforcement Learning for Vision-Based Drone Flightcited by 15
  5. 2022Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computerscited by 13
  6. 2023Reinforcement Learning for Safe Robot Control using Control Lyapunov Barrier Functionscited by 13
  7. 2022Physics Embedded Neural Network Vehicle Model and Applications in Risk-Aware Autonomous Driving Using Latent Featurescited by 12
  8. 2022NanoFlowNet: Real-time Dense Optical Flow on a Nano Quadcoptercited by 10
  9. 2026SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotorscited by 9
  10. 2021ModelLight: Model-Based Meta-Reinforcement Learning for Traffic Signal Controlcited by 8
  11. 2021Inclined Quadrotor Landing using Deep Reinforcement Learningcited by 7
  12. 2023Bridging Active Exploration and Uncertainty-Aware Deployment Using Probabilistic Ensemble Neural Network Dynamicscited by 7
  13. 2021Data-Efficient Deep Reinforcement Learning for Attitude Control of Fixed-Wing UAVs: Field Experimentscited by 6
  14. 2022Using Simulation Optimization to Improve Zero-shot Policy Transfer of Quadrotorscited by 4
  15. 2023HyperPPO: A scalable method for finding small policies for robotic controlcited by 4
  16. 2021Learning on Abstract Domains: A New Approach for Verifiable Guarantee in Reinforcement Learningcited by 3
  17. 2021Reinforcement Learning with Formal Performance Metrics for Quadcopter Attitude Control under Non-nominal Contextscited by 3
  18. 2024LiRA: Light-Robust Adversary for Model-based Reinforcement Learning in Real Worldcited by 3
  19. 2021Low-level Pose Control of Tilting Multirotor for Wall Perching Tasks Using Reinforcement Learningcited by 2
  20. 2025Equivariant Reinforcement Learning Frameworks for Quadrotor Low-Level Controlcited by 2
  21. 2025End-to-End Low-Level Neural Control of an Industrial-Grade 6D Magnetic Levitation Systemcited by 2
  22. 2025Multi-Robot Collaboration through Reinforcement Learning and Abstract Simulationcited by 1
  23. 2026Integrating Lagrangian Neural Networks into the Dyna Framework for Reinforcement Learningcited by 1
  24. 2021Data-driven controllers and the need for perception systems in underwater manipulationcited by 0
  25. 2021Training Lightweight CNNs for Human-Nanodrone Proximity Interaction from Small Datasets using Background Randomizationcited by 0
  26. 2022Designing a Robust Low-Level Agnostic Controller for a Quadrotor with Actor-Critic Reinforcement Learningcited by 0
  27. 2024Proto-MPC: An Encoder-Prototype-Decoder Approach for Quadrotor Control in Challenging Windscited by 0
  28. 2025Vision-Based System Identification of a Quadrotorcited by 0
  29. 2026World-Task Factorization for Robot Learningcited by 0
  30. 2026A New Quaternion-Joint Cable-Driven Redundant Manipulator Configuration and its Control Through FABRIK and Residual Reinforcement Learningcited by 0
  31. 2026Merging model-based control with multi-agent reinforcement learning for multi-agent cooperative teaming strategiescited by 0
  32. 2026Trajectory Design and Budgeted Querying for Digital Twin Calibrationcited by 0