Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning

  • Rohan Chitnis
  • , Tom Silver
  • , Joshua B. Tenenbaum
  • , Tomas Lozano-Perez
  • , Leslie Pack Kaelbling

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

30 Scopus citations

Abstract

In robotic domains, learning and planning are complicated by continuous state spaces, continuous action spaces, and long task horizons. In this work, we address these challenges with Neuro-Symbolic Relational Transition Models (NSRTs), a novel class of models that are data-efficient to learn, compatible with powerful robotic planning methods, and generalizable over objects. NSRTs have both symbolic and neural components, enabling a bilevel planning scheme where symbolic AI planning in an outer loop guides continuous planning with neural models in an inner loop. Experiments in four robotic planning domains show that NSRTs can be learned very data-efficiently, and then used for fast planning in new tasks that require up to 60 actions and involve many more objects than were seen during training.

Original languageEnglish (US)
Title of host publication2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4166-4173
Number of pages8
ISBN (Electronic)9781665479271
DOIs
StatePublished - 2022
Externally publishedYes
Event2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022 - Kyoto, Japan
Duration: Oct 23 2022Oct 27 2022

Publication series

NameIEEE International Conference on Intelligent Robots and Systems
Volume2022-October
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866

Conference

Conference2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022
Country/TerritoryJapan
CityKyoto
Period10/23/2210/27/22

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Software
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning'. Together they form a unique fingerprint.

Cite this