Long-Term Planning with Deep Reinforcement Learning on Autonomous Drones

TL;DR

This paper demonstrates long-term planning for autonomous drones using deep reinforcement learning trained with PPO, successfully competing against classical algorithms in a simulated drone racing environment.

Contribution

It introduces a reinforcement learning approach with opponent GPS data for efficient training in drone racing scenarios, validated in a realistic simulation environment.

Findings

RL agent outperforms classical path planning algorithms

Opponent GPS data improves training stability and efficiency

Reproducible code available on GitHub

Abstract

In this paper, we study a long-term planning scenario that is based on drone racing competitions held in real life. We conducted this experiment on a framework created for "Game of Drones: Drone Racing Competition" at NeurIPS 2019. The racing environment was created using Microsoft's AirSim Drone Racing Lab. A reinforcement learning agent, a simulated quadrotor in our case, has trained with the Policy Proximal Optimization(PPO) algorithm was able to successfully compete against another simulated quadrotor that was running a classical path planning algorithm. Agent observations consist of data from IMU sensors, GPS coordinates of drone obtained through simulation and opponent drone GPS information. Using opponent drone GPS information during training helps dealing with complex state spaces, serving as expert guidance allows for efficient and stable training process. All experiments performed in this paper can be found and reproduced with code at our GitHub repository