Efficiency-reinforced Learning with Auxiliary Depth Reconstruction for Autonomous Navigation of Mobile Devices

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

4 Scopus citations

Abstract

In this paper, we take Unmanned Aerial Vehicles (UAVs) as the mobile devices to study the problem of autonomous navigation since UAVs have been adopted as intelligent vehicles for executing complex tasks such as bridge structure examination, crowd estimation, target searching, and package delivery. As Deep Reinforcement Learning (DRL) has achieved great success in many control tasks, it is envisaged to exploit DRL for autonomous navigation. Nevertheless, as the navigation path becomes distant, searching in a large number of states and action spaces becomes very challenging to DRL. In this paper, we provide a novel reinforcement learning framework to facilitate the autonomous navigation in complicated environments by jointly considering the temporal abstractions and policy efficiency to dynamically select the frequency of the action decisions with the efficiency regularization. Moreover, to bootstrap the learning procedure, we further add an auxiliary task of depth map reconstruction to accelerate the learning process. Experimental results on 3D UAV simulator and DeepMind Lab environments manifest that the proposed framework improves the state-of-the-art methods in terms of success rates in different environments.

Original languageEnglish
Title of host publicationProceedings - 2022 23rd IEEE International Conference on Mobile Data Management, MDM 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages458-463
Number of pages6
ISBN (Electronic)9781665451765
DOIs
StatePublished - 2022
Event23rd IEEE International Conference on Mobile Data Management, MDM 2022 - Virtual, Paphos, Cyprus
Duration: 6 Jun 20229 Jun 2022

Publication series

NameProceedings - IEEE International Conference on Mobile Data Management
Volume2022-June
ISSN (Print)1551-6245

Conference

Conference23rd IEEE International Conference on Mobile Data Management, MDM 2022
Country/TerritoryCyprus
CityVirtual, Paphos
Period6/06/229/06/22

Keywords

  • Autonomous navigation
  • reinforcement learning
  • unmanned aerial vehicle

Fingerprint

Dive into the research topics of 'Efficiency-reinforced Learning with Auxiliary Depth Reconstruction for Autonomous Navigation of Mobile Devices'. Together they form a unique fingerprint.

Cite this