Jin, Y, Paredes Soto, DA, Rossiter, J orcid.org/0000-0002-1336-0633 et al. (1 more author) (2021) Advanced environment modelling for remote teleoperation to improve operator experience. In: icARTi '21: Proceedings of the International Conference on Artificial Intelligence and its Applications. 2021 International Conference on Artificial Intelligence and its Applications (ICARTI 2021), 09-10 Dec 2021, Bagatelle, Mauritius (Virtual). Association for Computing Machinery ISBN 9781450385756
Abstract
This work presents a novel intelligent robot perception system, including a real-time, high-quality, 3D scanning pipeline for texture-less scenes and a human-supervised grasping system. Comparison is carried out with the state of the art 3D reconstruction systems, and the performance of the proposed system is demonstrated. The scanning methods are applied to a new user interface with object 6D-pose estimation. This work supports human-robot interaction in remote handling operations in hazardous environments by providing a high-quality telepresence. Current teleoperation systems primarily utilise 2D images or point clouds to display the remote workspace to the operator. Operators require extensive training to be able to perceive the spatial relationship between the robot and the target objects by remotely looking at multiple 2D images. Therefore, this paper proposes a new teleoperation system that exploits artificial intelligence to improve the efficiency of operators. The experiments show that the proposed method surpasses state-of-the-art reconstruction systems and successfully complements a simulated nuclear waste handling experiment.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2021 Association for Computing Machinery. This is an author-produced version of a paper subsequently published in icARTi '21: Proceedings of the International Conference on Artificial Intelligence and its Applications. Uploaded in accordance with the publisher's self-archiving policy. |
Keywords: | human-robot interaction; semi-autonomous system; 3D environment reconstruction; 3D object detection |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Automatic Control and Systems Engineering (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 09 Sep 2021 15:49 |
Last Modified: | 08 Mar 2022 20:22 |
Status: | Published |
Publisher: | Association for Computing Machinery |
Refereed: | Yes |
Identification Number: | 10.1145/3487923.3487939 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:177450 |