RELAX: Reinforcement Learning Enabled 2D-LiDAR Autonomous System for Parsimonious UAVs

TL;DR

RELAX is a cost-efficient autonomous UAV system that uses only a single 2D-LiDAR and reinforcement learning to navigate complex environments more robustly than existing methods.

Contribution

It introduces RELAX, an end-to-end framework combining map construction, offline planning, and RL-based online re-planning for UAVs with minimal hardware.

Findings

More robust dynamic navigation than existing algorithms

Significantly lower hardware costs

Effective in unknown environments

Abstract

Unmanned Aerial Vehicles (UAVs) have become increasingly prominence in recent years, finding applications in surveillance, package delivery, among many others. Despite considerable efforts in developing algorithms that enable UAVs to navigate through complex unknown environments autonomously, they often require expensive hardware and sensors, such as RGB-D cameras and 3D-LiDAR, leading to a persistent trade-off between performance and cost. To this end, we propose RELAX, a novel end-to-end autonomous framework that is exceptionally cost-efficient, requiring only a single 2D-LiDAR to enable UAVs operating in unknown environments. Specifically, RELAX comprises three components: a pre-processing map constructor; an offline mission planner; and a reinforcement learning (RL)-based online re-planner. Experiments demonstrate that RELAX offers more robust dynamic navigation compared to existing algorithms, while only costing a fraction of the others. The code will be made public upon acceptance.