ポテンシャル法と深層強化学習を用いたクアッドロータの自律的障害物回避

• 白石 大介

  明治大学理工学部

• 市原 裕之

  明治大学理工学部

書誌事項

タイトル別名

• Obstacle Avoidance of a Quadrotor Based on Potential Field Method with Deep Reinforcement Learning
• ポテンシャルホウ ト シンソウ キョウカ ガクシュウ オ モチイタ クアッドロータ ノ ジリツテキ ショウガイブツ カイヒ

抄録

In motion planning of robots such as quadrotors, potential field methods are useful so that robots avoid obstacles. The artificial potential field method, which is one of the potential field ones, enables us to plan actions. However, the quadrotors sometimes fail to avoid the obstacles because the artificial potential field method does not take into consideration the inertia effect arising from the velocity of the quadrotors. To overcome the inertia effect, we give an idea of applying deep reinforcement learning to the artificial potential field method to determine an additional reference signal to the quadrotor. Thanks to this reference signal, the quadrotor improves the performance in trial and error to avoid the obstacles. Then the robot achieves an optimal action from the velocity of the robot and the position of the obstacles.

収録刊行物

• 計測自動制御学会論文集

  計測自動制御学会論文集 56 (3), 156-166, 2020

  公益社団法人 計測自動制御学会

キーワード

• quadrotor
• potential field method
• reinforcement learning
• motion planning

詳細情報

• CRID: 1390283659859354880
• NII論文ID: 130007809727
• NII書誌ID: AN00072392
• DOI: 10.9746/sicetr.56.156
• ISSN: 18838189
• ISSN: 04534654
• NDL書誌ID: 030327082
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I030327082
• Web Site: https://www.jstage.jst.go.jp/article/sicetr/56/3/56_156/_pdf
• 本文言語コード: ja
• データソース種別:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
  • KAKEN
• 抄録ライセンスフラグ: 使用不可