Uploaded May 2025 | Updated November 2026, 3 hours ago
This work presents the first neural network controller for drone racing that generalizes across physically distinct quadcopters. We demonstrate that a single network, trained with domain randomization, can robustly control various types of quadcopters. The network relies solely on the current state to directly compute motor commands. The effectiveness of this generalized controller is validated through real-world tests on two substantially different crafts (3-inch and 5-inch race quadcopters).
paper: arxiv.org/pdf/2504.21586
code: github.com/tudelft/optimal_quad_control_RL
This work presents the first neural network controller for drone racing that generalizes across physically distinct quadcopters. We demonstrate that a single network, trained with domain randomization, can robustly control various types of quadcopters. The network relies solely on the current state to directly compute motor commands. The effectiveness of this generalized controller is validated through real-world tests on two substantially different crafts (3-inch and 5-inch race quadcopters).
paper: arxiv.org/pdf/2504.21586
code: github.com/tudelft/optimal_quad_control_RL










