mlsanityData to 14 Oct 2026

TACO: General Acrobatic Flight Control via Target-and-Command-Oriented Reinforcement Learning

arXiv 2503.01125 ↗First posted 3 Mar 2025cs.ROcited by 3

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

Abstract (arXiv)

Although acrobatic flight control has been studied extensively, one key limitation of the existing methods is that they are usually restricted to specific maneuver tasks and cannot change flight pattern parameters online. In this work, we propose a target-and-command-oriented reinforcement learning (TACO) framework, which can handle different maneuver tasks in a unified way and allows online parameter changes. Additionally, we propose a spectral normalization method with input-output rescaling to enhance the policy's temporal and spatial smoothness, independence, and symmetry, thereby overcoming the sim-to-real gap. We validate the TACO approach through extensive simulation and real-world experiments, demonstrating its capability to achieve high-speed circular flights and continuous multi-flips.

Key facts. Cited by 3 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 27 of its 39 references that are in the map. First posted on arXiv 3 Mar 2025.

Builds on

27 of 39 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Multi-Task Reinforcement Learning for Quadrotors17 Dec

Other references · 26

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  3. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  4. 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 187
  5. 2022Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behaviorcited by 138
  6. 2023Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learningcited by 111
  7. 2020Flightmare: A Flexible Quadrotor Simulatorcited by 84
  8. 2020Deep Drone Acrobaticscited by 75
  9. 2020Regularizing Action Policies for Smooth Control with Reinforcement Learningcited by 59
  10. 2022A Benchmark Comparison of Learned Control Policies for Agile Quadrotor Flightcited by 47
  11. 2021NeuroBEM: Hybrid Aerodynamic Quadrotor Modelcited by 37
  12. 2021Data-Driven MPC for Quadrotorscited by 35
14 more
  1. 2017Differential Flatness of Quadrotor Dynamics Subject to Rotor Drag for Accurate Tracking of High-Speed Trajectoriescited by 32
  2. 2020Perspectives on Sim2Real Transfer for Robotics: A Summary of the R:SS 2020 Workshopcited by 25
  3. 2021A Comparative Study of Nonlinear MPC and Differential-Flatness-Based Control for Quadrotor Agile Flightcited by 24
  4. 2022Learning a Single Near-hover Position Controller for Vastly Different Quadcopterscited by 21
  5. 2019Aggressive Online Control of a Quadrotor via Deep Network Representations of Optimality Principlescited by 10
  6. 2021Flying Through a Narrow Gap Using End-to-end Deep Reinforcement Learning Augmented with Curriculum Learning and Sim2Realcited by 10
  7. 2023Learning Agile Flights through Narrow Gaps with Varying Angles using Onboard Sensingcited by 8
  8. 2016Aggressive Quadrotor Flight through Narrow Gaps with Onboard Sensing and Computing using Active Visioncited by 7
  9. 2020How to Train your Quadrotor: A Framework for Consistently Smooth and Responsive Flight Control via Reinforcement Learningcited by 7
  10. 2021Range, Endurance, and Optimal Speed Estimates for Multicopterscited by 6
  11. 2022User-Conditioned Neural Control Policies for Mobile Roboticscited by 4
  12. 2022Aerobatic Trajectory Generation for a VTOL Fixed-Wing Aircraft Using Differential Flatnesscited by 3
  13. 2023Optimal Spatial-Temporal Triangulation for Bearing-Only Cooperative Motion Estimationcited by 3
  14. 2023Catch Planner: Catching High-Speed Targets in the Flightcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Mastering Diverse, Unknown, and Cluttered Tracks for Robust Vision-Based Drone Racingcited by 3
  2. 2026Multi-Task Reinforcement Learning of Drone Aerobatics by Exploiting Geometric Symmetriescited by 0
  3. 2026ASTER: Attitude-aware Suspended-payload Quadrotor Traversal via Efficient Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Reactive Aerobatic Flight via Reinforcement Learning
  2. 2025Learning Acrobatic Flight from Preferences
  3. 2025Simultaneous learning of state-to-state minimum-time planning and control ↗
  4. 2025Lyapunov Function-guided Reinforcement Learning for Flight Control
  5. 2026Online Action-Stacking Improves Reinforcement Learning Performance for Air Traffic Control
  6. 2025Reinforcement Learning for Gliding Projectile Guidance and Control
  7. 2024ConcertoRL: An Innovative Time-Interleaved Reinforcement Learning Approach for Enhanced Control in Direct-Drive Tandem-Wing Vehicles
  8. 2025Learning Agile Gate Traversal via Analytical Optimal Policy Gradient