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

Zikang Yin; Canlun Zheng; Shiliang Guo; Zhikun Wang; Shiyu Zhao

IROS 20253 citations

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

Zikang Yin, Canlun Zheng, Shiliang Guo, Zhikun Wang, Shiyu Zhao

Abstract

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. We also 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 ability to achieve high-speed, high-accuracy circular flights and continuous multi-flips. The code is available at https://github.com/yinzikang/TACO.

BibTeX

@inproceedings{iros2025_tacogeneralacrob,
  title = {TACO: General Acrobatic Flight Control via Target-and-Command-Oriented Reinforcement Learning},
  author = {Zikang Yin and Canlun Zheng and Shiliang Guo and Zhikun Wang and Shiyu Zhao},
  booktitle = {IROS 2025},
  year = {2025}
}