Explain Yourself: A Natural Language Interface for Scrutable Autonomous Robots

Francisco Javier Chiyah Garcia; David Robb; Xingkun Liu; Atanas Laskov; Pedro Patron; Helen Hastie

Explain Yourself: A Natural Language Interface for Scrutable Autonomous Robots

Francisco Javier Chiyah Garcia, David Robb, Xingkun Liu, Atanas Laskov, Pedro Patron, Helen Hastie

Research output: Contribution to conference › Paper › peer-review

Abstract / Description of output

Autonomous systems in remote locations have a high degree of autonomy and there is a need to explain what they are doing and why in order to increase transparency and maintain trust. Here, we describe a natural language chat interface that enables vehicle behaviour to be queried by the user. We obtain an interpretable model of autonomy through having an expert 'speak out-loud' and provide explanations during a mission. This approach is agnostic to the type of autonomy model and as expert and operator are from the same user-group, we predict that these explanations will align well with the operator's mental model, increase transparency and assist with operator training.

Original language	English
Pages	1-2
Number of pages	2
Publication status	Published - 1 Mar 2018
Event	Explainable Robotic Systems: Workshop in conjunction with the 13th Annual ACM/IEEE International Conference on Human Robot Interaction (HRI 2018) - Chicago, United States Duration: 5 Mar 2018 → 5 Mar 2018 https://explainableroboticsystems.wordpress.com/

Workshop

Workshop	Explainable Robotic Systems
Country/Territory	United States
City	Chicago
Period	5/03/18 → 5/03/18
Internet address	https://explainableroboticsystems.wordpress.com/

Access to Document

https://arxiv.org/abs/1803.02088Licence: All Rights Reserved

Cite this

@conference{a532b7e7be97475ba590f124e93b904b,

title = "Explain Yourself: A Natural Language Interface for Scrutable Autonomous Robots",

abstract = "Autonomous systems in remote locations have a high degree of autonomy and there is a need to explain what they are doing and why in order to increase transparency and maintain trust. Here, we describe a natural language chat interface that enables vehicle behaviour to be queried by the user. We obtain an interpretable model of autonomy through having an expert 'speak out-loud' and provide explanations during a mission. This approach is agnostic to the type of autonomy model and as expert and operator are from the same user-group, we predict that these explanations will align well with the operator's mental model, increase transparency and assist with operator training.",

author = "Garcia, {Francisco Javier Chiyah} and David Robb and Xingkun Liu and Atanas Laskov and Pedro Patron and Helen Hastie",

year = "2018",

month = mar,

day = "1",

language = "English",

pages = "1--2",

note = "Explainable Robotic Systems : Workshop in conjunction with the 13th Annual ACM/IEEE International Conference on Human Robot Interaction (HRI 2018) ; Conference date: 05-03-2018 Through 05-03-2018",

url = "https://explainableroboticsystems.wordpress.com/",

}

TY - CONF

T1 - Explain Yourself: A Natural Language Interface for Scrutable Autonomous Robots

AU - Garcia, Francisco Javier Chiyah

AU - Robb, David

AU - Liu, Xingkun

AU - Laskov, Atanas

AU - Patron, Pedro

AU - Hastie, Helen

PY - 2018/3/1

Y1 - 2018/3/1

N2 - Autonomous systems in remote locations have a high degree of autonomy and there is a need to explain what they are doing and why in order to increase transparency and maintain trust. Here, we describe a natural language chat interface that enables vehicle behaviour to be queried by the user. We obtain an interpretable model of autonomy through having an expert 'speak out-loud' and provide explanations during a mission. This approach is agnostic to the type of autonomy model and as expert and operator are from the same user-group, we predict that these explanations will align well with the operator's mental model, increase transparency and assist with operator training.

AB - Autonomous systems in remote locations have a high degree of autonomy and there is a need to explain what they are doing and why in order to increase transparency and maintain trust. Here, we describe a natural language chat interface that enables vehicle behaviour to be queried by the user. We obtain an interpretable model of autonomy through having an expert 'speak out-loud' and provide explanations during a mission. This approach is agnostic to the type of autonomy model and as expert and operator are from the same user-group, we predict that these explanations will align well with the operator's mental model, increase transparency and assist with operator training.

M3 - Paper

SP - 1

EP - 2

T2 - Explainable Robotic Systems

Y2 - 5 March 2018 through 5 March 2018

ER -

Explain Yourself: A Natural Language Interface for Scrutable Autonomous Robots

Abstract / Description of output

Workshop

Access to Document

Fingerprint

Cite this