Context Dependent Trajectory Generation using Sequence-to-Sequence Models for Robotic Toilet Cleaning

Pin Chu Yang, Nishanth Koganti, Gustavo Alfonso Garcia Ricardez, Masaki Yamamoto, Jun Takamatsu, Tsukasa Ogasawara

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

2 Citations (Scopus)

Abstract

A robust, easy-to-deploy robot for service tasks in a real environment is difficult to construct. Record-and-playback (RP) is a method used to teach motor-skills to robots for performing service tasks. However, RP methods do not scale to challenging tasks where even slight changes in the environment, such as localization errors, would either require trajectory modification or a new demonstration. In this paper, we propose a Sequence-to-Sequence (Seq2Seq) based neural network model to generate robot trajectories in configuration space given a context variable based on real-world measurements in Cartesian space. We use the offset between a target pose and the actual pose after localization as the context variable. The model is trained using a few expert demonstrations collected using teleoperation. We apply our proposed method to the task of toilet cleaning where the robot has to clean the surface of a toilet bowl using a compliant end-effector in a constrained toilet setting. In the experiments, the model is given a novel offset context and it generates a modified robot trajectory for that context. We demonstrate that our proposed model is able to generate trajectories for unseen setups and the executed trajectory results in cleaning of the toilet bowl.

Original languageEnglish
Title of host publication29th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages932-937
Number of pages6
ISBN (Electronic)9781728160757
DOIs
Publication statusPublished - 2020 Aug
Externally publishedYes
Event29th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2020 - Virtual, Naples, Italy
Duration: 2020 Aug 312020 Sep 4

Publication series

Name29th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2020

Conference

Conference29th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2020
Country/TerritoryItaly
CityVirtual, Naples
Period20/8/3120/9/4

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Social Psychology
  • Communication

Fingerprint

Dive into the research topics of 'Context Dependent Trajectory Generation using Sequence-to-Sequence Models for Robotic Toilet Cleaning'. Together they form a unique fingerprint.

Cite this