From explanation to synthesis: compositional program induction for learning from demonstration

Michael Burke, Svetlin Penkov, Subramanian Ramamoorthy

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

12 Citations (Scopus)

Abstract

Hybrid systems are a compact and natural mechanism with which to address problems in robotics. This work introduces an approach to learning hybrid systems from demonstrations, with an emphasis on extracting models that are explicitly verifiable and easily interpreted by robot operators. We fit a sequence of controllers using sequential importance sampling under a generative switching proportional controller task model. Here, we parameterise controllers using a proportional gain and a visually verifiable joint angle goal. Inference under this model is challenging, but we address this by introducing an attribution prior extracted from a neural end-to-end visuomotor control model. Given the sequence of controllers comprising a task, we simplify the trace using grammar parsing strategies, taking advantage of the sequence compositionality, before grounding the controllers by training perception networks to predict goals given images. Using this approach, we are successfully able to induce a program for a visuomotor reaching task involving loops and conditionals from a single demonstration and a neural end-to-end model. In addition, we are able to discover the program used for a tower building task. We argue that computer program-like control systems are more interpretable than alternative end-to-end learning approaches, and that hybrid systems inherently allow for better generalisation across task configurations.

Original languageEnglish
Title of host publicationProceedings of Robotics: Science and Systems 2019
EditorsAntonio Bicchi, Hadas Kress-Gazit , Seth Hutchinson
Place of PublicationFreiburg im Breisgau Germany
PublisherRobotics: Science and Systems Foundation
Pages1-10
Number of pages10
VolumeXV
ISBN (Print)9780992374754
DOIs
Publication statusPublished - 2019
Externally publishedYes
EventRobotics: Science and Systems 2019 - Freiburg im Breisgau, Germany
Duration: 22 Jun 201926 Jun 2019
Conference number: 15th
http://rss2019.informatik.uni-freiburg.de (Website)
http://www.roboticsproceedings.org (Proceedings)

Publication series

NameRobotics: Science and Systems
ISSN (Electronic)2330-765X

Conference

ConferenceRobotics: Science and Systems 2019
Abbreviated titleRSS 2019
Country/TerritoryGermany
CityFreiburg im Breisgau
Period22/06/1926/06/19
Internet address

Cite this