A parameter sharing method for reinforcement learning model between AirSim and UAVs

Chia Yu Ho, Shau Yin Tseng, Chin Feng Lai, Ming Shi Wang, Ching Ju Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In recent years, unmanned aerial vehicle aerial photography has developed rapidly. Unmanned aerial vehicle can get a different perspective and allow us to do more difficult tasks. Controlling unmanned aerial vehicle requires a lot of manpower, so there are a number of studies that use reinforcement learning to make the unmanned aerial vehicle fly autonomously. It is an expensive and time-consuming task to use reinforcement learning and training unmanned aerial vehicle to accomplish specific tasks in a realistic environment. Therefore this study in a virtual environment using the Q - learning training unmanned aerial vehicle landing, then transplanted model of virtual environment in which to train good into real environment, makes the realistic environment of unmanned aerial vehicle can use cheaper and quickly achieve the same task.

Original languageEnglish
Title of host publicationProceedings - 2018 1st International Cognitive Cities Conference, IC3 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages20-23
Number of pages4
ISBN (Electronic)9781538650592
DOIs
Publication statusPublished - 2018 Dec 6
Event1st International Cognitive Cities Conference, IC3 2018 - Okinawa, Japan
Duration: 2018 Aug 72018 Aug 9

Publication series

NameProceedings - 2018 1st International Cognitive Cities Conference, IC3 2018

Other

Other1st International Cognitive Cities Conference, IC3 2018
CountryJapan
CityOkinawa
Period18-08-0718-08-09

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Education
  • Urban Studies

Fingerprint Dive into the research topics of 'A parameter sharing method for reinforcement learning model between AirSim and UAVs'. Together they form a unique fingerprint.

Cite this