Learning multi-stage tasks with one demonstration via self-replay
File(s)
Published version
OA Location
Author(s)
Johns, Edward
Di Palo, Norman
Type
Conference Paper
Abstract
In this work, we introduce a novel method to learn everyday-like multistage tasks from a single human demonstration, without requiring any prior object
knowledge. Inspired by the recent Coarse-to-Fine Imitation Learning method, we
model imitation learning as a learned object reaching phase followed by an openloop replay of the demonstrator’s actions. We build upon this for multi-stage tasks
where, following the human demonstration, the robot can autonomously collect
image data for the entire multi-stage task, by reaching the next object in the sequence and then replaying the demonstration, and then repeating in a loop for all
stages of the task. We evaluate with real-world experiments on a set of everydaylike multi-stage tasks, which we show that our method can solve from a single
demonstration. Videos and supplementary material can be found at this webpage.
knowledge. Inspired by the recent Coarse-to-Fine Imitation Learning method, we
model imitation learning as a learned object reaching phase followed by an openloop replay of the demonstrator’s actions. We build upon this for multi-stage tasks
where, following the human demonstration, the robot can autonomously collect
image data for the entire multi-stage task, by reaching the next object in the sequence and then replaying the demonstration, and then repeating in a loop for all
stages of the task. We evaluate with real-world experiments on a set of everydaylike multi-stage tasks, which we show that our method can solve from a single
demonstration. Videos and supplementary material can be found at this webpage.
Date Issued
2021-11-11
Date Acceptance
2021-09-14
Citation
2021, pp.1-10
Publisher
OpenReview
Start Page
1
End Page
10
Copyright Statement
© 2021 The Author(s)
Sponsor
Royal Academy of Engineering
Identifier
https://openreview.net/forum?id=p-TBwVowXRH
Source
Conference on Robot Learning (CoRL) 2021
Publication Status
Accepted
Start Date
2021-11-08
Finish Date
2021-11-11
Coverage Spatial
London, UK
Date Publish Online
2021-11-11