Search papers, labs, and topics across Lattice.
This paper introduces a reinforcement learning framework for UAVs that simultaneously learns minimum-time state-to-state planning and control policies generalizable to arbitrary start and goal states. The method uses Point Mass Model (PMM) trajectories as proxy rewards to approximate optimal flight and curriculum learning to improve training efficiency and generalization. Simulation and real-world experiments demonstrate the learned policy's ability to perform agile flight and stable hovering while generalizing to new environments and running on embedded hardware.
Drones can now learn to fly between arbitrary points in minimum time using RL, even on a small ARM computer.
This paper tackles the challenge of learning a generalizable minimum-time flight policy for UAVs, capable of navigating between arbitrary start and goal states while balancing agile flight and stable hovering. Traditional approaches, particularly in autonomous drone racing, achieve impressive speeds and agility but are constrained to predefined track layouts, limiting real-world applicability. To address this, we propose a reinforcement learning-based framework that simultaneously learns state-to-state minimum-time planning and control and generalizes to arbitrary state-to-state flights. Our approach leverages Point Mass Model (PMM) trajectories as proxy rewards to approximate the true optimal flight objective and employs curriculum learning to scale the training process efficiently and to achieve generalization. We validate our method through simulation experiments, comparing it against Nonlinear Model Predictive Control (NMPC) tracking PMM-generated trajectories and conducting ablation studies to assess the impact of curriculum learning. Finally, real-world experiments confirm the robustness of our learned policy in outdoor environments, demonstrating its ability to generalize and operate on a small ARM-based single-board computer.
