TACO: General Acrobatic Flight Control via Target-and-Command-Oriented Reinforcement Learning
This work addresses the limitation of existing acrobatic flight control methods that are restricted to specific maneuvers and cannot change parameters online, providing a more flexible solution for drone acrobatics.
TACO proposes a unified reinforcement learning framework for acrobatic flight control that handles multiple maneuver tasks and allows online parameter changes, achieving high-speed circular flights and continuous multi-flips in real-world experiments.
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.