Transferable Task Execution from Pixels through Deep Planning Domain Learning

Kei Kase, Chris Paxton, Hammad Mazhar, Tetsuya Ogata, Dieter Fox

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

While robots can learn models to solve many manipulation tasks from raw visual input, they cannot usually use these models to solve new problems. On the other hand, symbolic planning methods such as STRIPS have long been able to solve new problems given only a domain definition and a symbolic goal, but these approaches often struggle on the real world robotic tasks due to the challenges of grounding these symbols from sensor data in a partially-observable world. We propose Deep Planning Domain Learning (DPDL), an approach that combines the strengths of both methods to learn a hierarchical model. DPDL learns a high-level model which predicts values for a large set of logical predicates consisting of the current symbolic world state, and separately learns a low-level policy which translates symbolic operators into executable actions on the robot. This allows us to perform complex, multistep tasks even when the robot has not been explicitly trained on them. We show our method on manipulation tasks in a photorealistic kitchen scenario.

本文言語English
ホスト出版物のタイトル2020 IEEE International Conference on Robotics and Automation, ICRA 2020
出版社Institute of Electrical and Electronics Engineers Inc.
ページ10459-10465
ページ数7
ISBN(電子版)9781728173955
DOI
出版ステータスPublished - 2020 5
イベント2020 IEEE International Conference on Robotics and Automation, ICRA 2020 - Paris, France
継続期間: 2020 5 312020 8 31

出版物シリーズ

名前Proceedings - IEEE International Conference on Robotics and Automation
ISSN(印刷版)1050-4729

Conference

Conference2020 IEEE International Conference on Robotics and Automation, ICRA 2020
国/地域France
CityParis
Period20/5/3120/8/31

ASJC Scopus subject areas

  • ソフトウェア
  • 制御およびシステム工学
  • 人工知能
  • 電子工学および電気工学

フィンガープリント

「Transferable Task Execution from Pixels through Deep Planning Domain Learning」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