TACO: General Acrobatic Flight Control via Target-and-Command-Oriented Reinforcement Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913131159093248 |
|---|---|
| author | Yin, Zikang Zheng, Canlun Guo, Shiliang Wang, Zhikun Zhao, Shiyu |
| author_facet | Yin, Zikang Zheng, Canlun Guo, Shiliang Wang, Zhikun Zhao, Shiyu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01125 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TACO: General Acrobatic Flight Control via Target-and-Command-Oriented Reinforcement Learning Yin, Zikang Zheng, Canlun Guo, Shiliang Wang, Zhikun Zhao, Shiyu Robotics 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. |
| title | TACO: General Acrobatic Flight Control via Target-and-Command-Oriented Reinforcement Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2503.01125 |