Transferable Task Execution from Pixels through Deep Planning Domain Learning

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

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

Abstract

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.

Original languageEnglish
Title of host publication2020 IEEE International Conference on Robotics and Automation, ICRA 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages10459-10465
Number of pages7
ISBN (Electronic)9781728173955
DOIs
Publication statusPublished - 2020 May
Event2020 IEEE International Conference on Robotics and Automation, ICRA 2020 - Paris, France
Duration: 2020 May 312020 Aug 31

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)1050-4729

Conference

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

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Transferable Task Execution from Pixels through Deep Planning Domain Learning'. Together they form a unique fingerprint.

Cite this