End-to-End Mobile Robot Navigation using a Residual Deep Reinforcement Learning in Dynamic Human Environments

Abdullah Ahmed*, Yasser F.O. Mohammad, Victor Parque, Haitham El-Hussieny, Sabah Ahmed

*この研究の対応する著者

研究成果: Conference contribution

抄録

Safe navigation through human crowds is key to enabling practical mobility ubiquitously. The Deep Reinforcement Learning (DRL) and the End-to-End (E2E) approaches to goal-oriented robot navigation have the potential to render policies able to tackle localization, path planning, obstacle avoidance, and adaptation to change in unison. In this paper, we report an architecture based on convolutional units and residual blocks being able to enhance adaptability to unseen and dynamic human environments. In particular, our scheme outperformed the state-of-the-art baselines SOADRL and NAVREP by about 13% and 18% on average success rate, respectively, throughout 27 unseen and dynamic navigation instances. Furthermore, our approach avoids the explicit encoding of positions and trajectories of moving humans compared to the standard models. Our results show the potential to render adaptive and generalizable policies for unknown and dynamic human environments.

本文言語English
ホスト出版物のタイトルMESA 2022 - 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ISBN(電子版)9781665455701
DOI
出版ステータスPublished - 2022
イベント18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, MESA 2022 - Virtual, Online, Taiwan, Province of China
継続期間: 2022 11月 282022 11月 30

出版物シリーズ

名前MESA 2022 - 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, Proceedings

Conference

Conference18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, MESA 2022
国/地域Taiwan, Province of China
CityVirtual, Online
Period22/11/2822/11/30

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ サイエンスの応用
  • 電子工学および電気工学
  • 機械工学
  • 制御と最適化
  • 器械工学

フィンガープリント

「End-to-End Mobile Robot Navigation using a Residual Deep Reinforcement Learning in Dynamic Human Environments」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル