Self-explainable robots in remote environments

Francisco J. Chiyah Garcia; Simón C. Smith; José Lopes; Subramanian Ramamoorthy; Helen Hastie

doi:10.1145/3434074.3447275

Self-explainable robots in remote environments

Francisco J. Chiyah Garcia, Simón C. Smith, José Lopes, Subramanian Ramamoorthy, Helen Hastie

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

As robots and autonomous systems become more adept at handling complex scenarios, their underlying mechanisms also become increasingly complex and opaque. This lack of transparency can give rise to unverifiable behaviours, limiting the use of robots in a number of applications including high-stakes scenarios, e.g. self-driving cars or first responders. In this paper and accompanying video, we present a system that learns from demonstrations to inspect areas in a remote environment and to explain robot behaviour. Using semi-supervised learning, the robot is able to inspect an offshore platform autonomously, whilst explaining its decision process both through both image-based and natural language-based interfaces.

Original language	English
Title of host publication	HRI '21 Companion
Subtitle of host publication	Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction
Publisher	Association for Computing Machinery
Pages	662-664
Number of pages	3
ISBN (Electronic)	9781450382908
DOIs	https://doi.org/10.1145/3434074.3447275
Publication status	Published - 8 Mar 2021
Event	2021 ACM/IEEE International Conference on Human-Robot Interaction - Virtual Conference, Boulder, United States Duration: 8 Mar 2021 → 11 Mar 2021 https://humanrobotinteraction.org/2021/

Conference

Conference	2021 ACM/IEEE International Conference on Human-Robot Interaction
Abbreviated title	HRI '21
Country/Territory	United States
City	Boulder
Period	8/03/21 → 11/03/21
Internet address	https://humanrobotinteraction.org/2021/

Keywords

Autonomous control
Explainable robot
Nlg
Remote location
Semi-supervised learning
Transparent interfaces

ASJC Scopus subject areas

Artificial Intelligence
Human-Computer Interaction
Electrical and Electronic Engineering

Access to Document

10.1145/3434074.3447275

Cite this

@inproceedings{12c85a4d0b5446a99806a382a8f16182,

title = "Self-explainable robots in remote environments",

abstract = "As robots and autonomous systems become more adept at handling complex scenarios, their underlying mechanisms also become increasingly complex and opaque. This lack of transparency can give rise to unverifiable behaviours, limiting the use of robots in a number of applications including high-stakes scenarios, e.g. self-driving cars or first responders. In this paper and accompanying video, we present a system that learns from demonstrations to inspect areas in a remote environment and to explain robot behaviour. Using semi-supervised learning, the robot is able to inspect an offshore platform autonomously, whilst explaining its decision process both through both image-based and natural language-based interfaces.",

keywords = "Autonomous control, Explainable robot, Nlg, Remote location, Semi-supervised learning, Transparent interfaces",

author = "{Chiyah Garcia}, {Francisco J.} and Smith, {Sim{\'o}n C.} and Jos{\'e} Lopes and Subramanian Ramamoorthy and Helen Hastie",

note = "Funding Information: This work was supported by the EPSRC-funded ORCA Hub (EP/R026173/1, 2017-2021) and UKRI Trustworthy Autonomous Systems Nodes in Trust (EP/V026682/1, 2020-2024) and in Governance and Regulation (EP/V026607/1, 2020-2024). Publisher Copyright: {\textcopyright} 2021 Owner/Author. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.; 2021 ACM/IEEE International Conference on Human-Robot Interaction, HRI '21 ; Conference date: 08-03-2021 Through 11-03-2021",

year = "2021",

month = mar,

day = "8",

doi = "10.1145/3434074.3447275",

language = "English",

pages = "662--664",

booktitle = "HRI '21 Companion",

publisher = "Association for Computing Machinery",

address = "United States",

url = "https://humanrobotinteraction.org/2021/",

}

Chiyah Garcia, FJ, Smith, SC, Lopes, J, Ramamoorthy, S & Hastie, H 2021, Self-explainable robots in remote environments. in HRI '21 Companion: Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction. Association for Computing Machinery, pp. 662-664, 2021 ACM/IEEE International Conference on Human-Robot Interaction, Boulder, Colorado, United States, 8/03/21. https://doi.org/10.1145/3434074.3447275

TY - GEN

T1 - Self-explainable robots in remote environments

AU - Chiyah Garcia, Francisco J.

AU - Smith, Simón C.

AU - Lopes, José

AU - Ramamoorthy, Subramanian

AU - Hastie, Helen

N1 - Funding Information: This work was supported by the EPSRC-funded ORCA Hub (EP/R026173/1, 2017-2021) and UKRI Trustworthy Autonomous Systems Nodes in Trust (EP/V026682/1, 2020-2024) and in Governance and Regulation (EP/V026607/1, 2020-2024). Publisher Copyright: © 2021 Owner/Author. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.

PY - 2021/3/8

Y1 - 2021/3/8

N2 - As robots and autonomous systems become more adept at handling complex scenarios, their underlying mechanisms also become increasingly complex and opaque. This lack of transparency can give rise to unverifiable behaviours, limiting the use of robots in a number of applications including high-stakes scenarios, e.g. self-driving cars or first responders. In this paper and accompanying video, we present a system that learns from demonstrations to inspect areas in a remote environment and to explain robot behaviour. Using semi-supervised learning, the robot is able to inspect an offshore platform autonomously, whilst explaining its decision process both through both image-based and natural language-based interfaces.

AB - As robots and autonomous systems become more adept at handling complex scenarios, their underlying mechanisms also become increasingly complex and opaque. This lack of transparency can give rise to unverifiable behaviours, limiting the use of robots in a number of applications including high-stakes scenarios, e.g. self-driving cars or first responders. In this paper and accompanying video, we present a system that learns from demonstrations to inspect areas in a remote environment and to explain robot behaviour. Using semi-supervised learning, the robot is able to inspect an offshore platform autonomously, whilst explaining its decision process both through both image-based and natural language-based interfaces.

KW - Autonomous control

KW - Explainable robot

KW - Nlg

KW - Remote location

KW - Semi-supervised learning

KW - Transparent interfaces

UR - http://www.scopus.com/inward/record.url?scp=85102763685&partnerID=8YFLogxK

U2 - 10.1145/3434074.3447275

DO - 10.1145/3434074.3447275

M3 - Conference contribution

AN - SCOPUS:85102763685

SP - 662

EP - 664

BT - HRI '21 Companion

PB - Association for Computing Machinery

T2 - 2021 ACM/IEEE International Conference on Human-Robot Interaction

Y2 - 8 March 2021 through 11 March 2021

ER -

Self-explainable robots in remote environments

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this