IRUS Total

Learning multi-stage tasks with one demonstration via self-replay

File Description SizeFormat 
learning_multi_stage_tasks_wit.pdfPublished version2.26 MBAdobe PDFView/Open
Title: Learning multi-stage tasks with one demonstration via self-replay
Authors: Johns, E
Di Palo, N
Item 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.
Issue Date: 11-Nov-2021
Date of Acceptance: 14-Sep-2021
URI: http://hdl.handle.net/10044/1/93296
Publisher: OpenReview
Start Page: 1
End Page: 10
Copyright Statement: © 2021 The Author(s)
Sponsor/Funder: Royal Academy of Engineering
Conference Name: Conference on Robot Learning (CoRL) 2021
Publication Status: Accepted
Start Date: 2021-11-08
Finish Date: 2021-11-11
Conference Place: London, UK
Open Access location: https://openreview.net/pdf?id=p-TBwVowXRH
Online Publication Date: 2021-11-11
Appears in Collections:Computing