Lander.AI: DRL-based Autonomous Drone Landing on Moving 3D Surface in the Presence of Aerodynamic Disturbances

Autonomous drone landing on dynamic platforms presents formidable challenges due to unpredictable velocities and aerodynamic disturbances. This study introduces an advanced Deep Reinforcement Learning (DRL) agent, Lander.AI, designed to navigate and land on 3D moving platforms in the presence of aerodynamic disturbance and sudden velocity changes, thereby enhancing drone autonomy and safety. Lander.AI is trained in the gym-pybullet-drone simulation, an environment that mirrors real-world complexities, including wind disturbance, to ensure the agent's robustness and adaptability. The agent's capabilities were empirically validated with Crazyflie 2.1 drones across various test scenarios, encompassing both simulated environments and real-world conditions. The experimental results showcased Lander.AI's high-precision landing and its ability to adapt to moving platforms, even under wind-induced disturbances. Furthermore, our system performance was bench-marked against a baseline Proportional-integral-derivative (PID) controller augmented with an Extended Kalman Filter (EKF), illustrating significant improvements in landing precision and error recovery. This research not only advances drone landing technologies, essential for inspection and emergency applications, but also highlights the potential of DRL in addressing intricate aerodynamic challenges.