Inclined Quadrotor Landing using Deep Reinforcement Learning
This addresses the problem of autonomous inclined landing for quadrotors, which is incremental as it applies existing DRL methods to a specific control challenge.
The paper tackled the problem of landing a quadrotor on an inclined surface, which is challenging due to the non-equilibrium final state, by proposing a deep reinforcement learning approach using PPO with sparse rewards and curriculum learning, resulting in a policy trained in simulation in under 90 minutes that successfully performs real landings with a single evaluation taking about 2.5 ms.
Landing a quadrotor on an inclined surface is a challenging maneuver. The final state of any inclined landing trajectory is not an equilibrium, which precludes the use of most conventional control methods. We propose a deep reinforcement learning approach to design an autonomous landing controller for inclined surfaces. Using the proximal policy optimization (PPO) algorithm with sparse rewards and a tailored curriculum learning approach, an inclined landing policy can be trained in simulation in less than 90 minutes on a standard laptop. The policy then directly runs on a real Crazyflie 2.1 quadrotor and successfully performs real inclined landings in a flying arena. A single policy evaluation takes approximately 2.5\,ms, which makes it suitable for a future embedded implementation on the quadrotor.