mlsanityData to 7 Oct 2026

Autonomous Drone Racing with Deep Reinforcement Learning

arXiv 2103.08624 ↗First posted 15 Mar 2021cs.RO cs.AIcited by 51

Not on the map. Why?

Abstract (arXiv)

In many robotic tasks, such as autonomous drone racing, the goal is to travel through a set of waypoints as fast as possible. A key challenge for this task is planning the time-optimal trajectory, which is typically solved by assuming perfect knowledge of the waypoints to pass in advance. The resulting solution is either highly specialized for a single-track layout, or suboptimal due to simplifying assumptions about the platform dynamics. In this work, a new approach to near-time-optimal trajectory generation for quadrotors is presented. Leveraging deep reinforcement learning and relative gate observations, our approach can compute near-time-optimal trajectories and adapt the trajectory to environment changes. Our method exhibits computational advantages over approaches based on trajectory optimization for non-trivial track configurations. The proposed approach is evaluated on a set of race tracks in simulation and the real world, achieving speeds of up to 60 km/h with a physical quadrotor.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). Builds on 18 of its 31 references that are in the map. First posted on arXiv 15 Mar 2021.

Builds on

18 of 31 references.

References · 18

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 494
  3. 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 342
  4. 2020Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehiclescited by 101
  5. 2017Control of a Quadrotor with Reinforcement Learningcited by 75
  6. 2020Flightmare: A Flexible Quadrotor Simulatorcited by 69
  7. 2020Deep Drone Acrobaticscited by 66
  8. 2020Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learningcited by 60
  9. 2017Optimization-Based Autonomous Racing of 1:43 Scale RC Carscited by 47
  10. 2018End-to-End Race Driving with Deep Reinforcement Learningcited by 38
  11. 2019Robust and Efficient Quadrotor Trajectory Generation for Fast Autonomous Flightcited by 32
  12. 2020AlphaPilot: Autonomous Drone Racingcited by 23
6 more
  1. 2018Beauty and the Beast: Optimal Methods Meet Learning for Drone Racingcited by 20
  2. 2019FlightGoggles: A Modular Framework for Photorealistic Camera, Exteroceptive Sensor, and Dynamics Simulationcited by 20
  3. 2020AirSim Drone Racing Labcited by 15
  4. 2017Minimum-time trajectory generation for quadrotors in constrained environmentscited by 4
  5. 2020Multi-Fidelity Black-Box Optimization for Time-Optimal Quadrotor Maneuverscited by 3
  6. 2020CPC: Complementary Progress Constraints for Time-Optimal Quadrotor Trajectoriescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 16; 2023: 14; 2024: 8; 2025: 7; 2026: 3.

51 papers.

Sort:

By area:

  1. 2023Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learningcited by 72
  2. 2023OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Controlcited by 28
  3. 2023DexPBT: Scaling up Dexterous Manipulation for Hand-Arm Systems with Population Based Trainingcited by 24
  4. 2024Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flightcited by 22
  5. 2022Optimizing Nitrogen Management with Deep Reinforcement Learning and Crop Simulationscited by 20
  6. 2023Learning to Fly in Secondscited by 18
  7. 2021Policy Search for Model Predictive Control with Application to Agile Drone Flightcited by 17
  8. 2022Learning a Single Near-hover Position Controller for Vastly Different Quadcopterscited by 16
  9. 2022Training Efficient Controllers via Analytic Policy Gradientcited by 16
  10. 2025Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learningcited by 14
  11. 2022Learning Perception-Aware Agile Flight in Cluttered Environmentscited by 13
  12. 2022Learning Deep Sensorimotor Policies for Vision-based Autonomous Drone Racingcited by 13
38 more
  1. 2024Multi-Task Reinforcement Learning for Quadrotorscited by 12
  2. 2022Position-Agnostic Autonomous Navigation in Vineyards with Deep Reinforcement Learningcited by 11
  3. 2023Contrastive Learning for Enhancing Robust Scene Transfer in Vision-based Agile Flightcited by 11
  4. 2023Vision-based Learning for Drones: A Surveycited by 9
  5. 2024What Matters in Learning A Zero-Shot Sim-to-Real RL Policy for Quadrotor Control? A Comprehensive Studycited by 9
  6. 2022Collaborative Target Search with a Visual Drone Swarm: An Adaptive Curriculum Embedded Multistage Reinforcement Learning Approachcited by 8
  7. 2023Learning Multi-Pursuit Evasion for Safe Targeted Navigation of Dronescited by 8
  8. 2024Learning to Boost the Performance of Stable Nonlinear Systemscited by 7
  9. 2022Neural Moving Horizon Estimation for Robust Flight Controlcited by 5
  10. 2022Probabilistic Verification of ReLU Neural Networks via Characteristic Functionscited by 5
  11. 2023Contrastive Initial State Buffer for Reinforcement Learningcited by 5
  12. 2022Equivariant Reinforcement Learning for Quadrotor UAVcited by 4
  13. 2022Efficiently Learning Small Policies for Locomotion and Manipulationcited by 4
  14. 2023Optimality Principles in Spacecraft Neural Guidance and Controlcited by 4
  15. 2023HyperPPO: A scalable method for finding small policies for robotic controlcited by 4
  16. 2021Socialbots on Fire: Modeling Adversarial Behaviors of Socialbots via Multi-Agent Hierarchical Reinforcement Learningcited by 3
  17. 2022Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic Locomotioncited by 3
  18. 2022PIC4rl-gym: a ROS2 modular framework for Robots Autonomous Navigation with Deep Reinforcement Learningcited by 3
  19. 2022Real-time Cooperative Vehicle Coordination at Unsignalized Road Intersectionscited by 2
  20. 2024SpecGuard: Specification Aware Recovery for Robotic Autonomous Vehicles from Physical Attackscited by 2
  21. 2025A Primer on SO(3) Action Representations in Deep Reinforcement Learningcited by 2
  22. 2022Parallel Reinforcement Learning Simulation for Visual Quadrotor Navigationcited by 1
  23. 2023Towards Dependable Autonomous Systems Based on Bayesian Deep Learning Componentscited by 1
  24. 2023Reinforcement Learning Based Self-play and State Stacking Techniques for Noisy Air Combat Environmentcited by 1
  25. 2023Differentially Encoded Observation Spaces for Perceptive Reinforcement Learningcited by 1
  26. 2023Optimal Cost Constrained Adversarial Attacks For Multiple Agent Systemscited by 1
  27. 2024NaviSplit: Dynamic Multi-Branch Split DNNs for Efficient Distributed Autonomous Navigationcited by 1
  28. 2024NaviSlim: Adaptive Context-Aware Navigation and Sensing via Dynamic Slimmable Networkscited by 1
  29. 2025Towards Task-Oriented Flying: Framework, Infrastructure, and Principlescited by 1
  30. 2026Constrained Meta Reinforcement Learning with Provable Test-Time Safetycited by 1
  31. 2026Wind-Aware Reinforcement Learning Control of a Small Quadrotor Using Learned Onboard Wind Estimation in Simulated Atmospheric Turbulencecited by 1
  32. 2021Robustifying Reinforcement Learning Policies with L1 Adaptive Controlcited by 0
  33. 2022Interactive Imitation Learning in Robotics based on Simulationscited by 0
  34. 2024Continual Learning for Robust Gate Detection under Dynamic Lighting in Autonomous Drone Racingcited by 0
  35. 2025Deep RL-based Autonomous Navigation of Micro Aerial Vehicles (MAVs) in a complex GPS-denied Indoor Environmentcited by 0
  36. 2025Decision Transformer-Based Drone Trajectory Planning with Dynamic Safety-Efficiency Trade-Offscited by 0
  37. 2025Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approachcited by 0
  38. 2025Self-Supervised Learning to Fly using Efficient Semantic Segmentation and Metric Depth Estimation for Low-Cost Autonomous UAVscited by 0

50 most cited of 51 All 51 (JSON)