Inclined Quadrotor Landing using Deep Reinforcement Learning

TL;DR

This paper introduces a deep reinforcement learning method for autonomous quadrotor landing on inclined surfaces, achieving real-world success with a policy trained efficiently in simulation and capable of real-time execution.

Contribution

The paper presents a novel RL-based approach for inclined quadrotor landing, demonstrating effective transfer from simulation to real-world without complex control schemes.

Findings

Successful real-world inclined landings on Crazyflie 2.1

Training in less than 90 minutes on a standard laptop

Real-time policy execution at 2.5 ms per evaluation

Abstract

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.