UAV Path Planning using Global and Local Map Information with Deep Reinforcement Learning

Mirco Theile, Harald Bayerlein, Richard Nai, David Gesbert, Marco Caccamo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

29 Scopus citations

Abstract

Path planning methods for autonomous unmanned aerial vehicles (UAVs) are typically designed for one specific type of mission. This work presents a method for autonomous UAV path planning based on deep reinforcement learning (DRL) that can be applied to a wide range of mission scenarios. Specifically, we compare coverage path planning (CPP), where the UAV's goal is to survey an area of interest to data harvesting (DH), where the UAV collects data from distributed Internet of Things (IoT) sensor devices. By exploiting structured map information of the environment, we train double deep Q-networks (DDQNs) with identical architectures on both distinctly different mission scenarios to make movement decisions that balance the respective mission goal with navigation constraints. By introducing a novel approach exploiting a compressed global map of the environment combined with a cropped but uncompressed local map showing the vicinity of the UAV agent, we demonstrate that the proposed method can efficiently scale to large environments. We also extend previous results for generalizing control policies that require no retraining when scenario parameters change and offer a detailed analysis of crucial map processing parameters' effects on path planning performance.

Original languageEnglish
Title of host publication2021 20th International Conference on Advanced Robotics, ICAR 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages539-546
Number of pages8
ISBN (Electronic)9781665436847
DOIs
StatePublished - 2021
Event20th International Conference on Advanced Robotics, ICAR 2021 - Ljubljana, Slovenia
Duration: 6 Dec 202110 Dec 2021

Publication series

Name2021 20th International Conference on Advanced Robotics, ICAR 2021

Conference

Conference20th International Conference on Advanced Robotics, ICAR 2021
Country/TerritorySlovenia
CityLjubljana
Period6/12/2110/12/21

Fingerprint

Dive into the research topics of 'UAV Path Planning using Global and Local Map Information with Deep Reinforcement Learning'. Together they form a unique fingerprint.

Cite this