The Muttering Robot: Improving Robot Transparency Though Vocalisation of Reactive Plan Execution

Robert H Wortham; Vivienne Rogers

The Muttering Robot: Improving Robot Transparency Though Vocalisation of Reactive Plan Execution

Robert H Wortham, Vivienne Rogers

Department of Computer Science

Research output: Contribution to conference › Paper

90 Downloads (Pure)

Abstract

Transparency is an important design consideration for all intelligent autonomous systems. Previous work shows that a real-time visual display of a robot’s decision making produces significantly better understanding of that robot’s intelligence. We investigate vocalisation of behaviour selection as a possible alternative solution for situations where a visual display of decision making is either impractical or impossible. In initial experiments we find that vocalisation is associated with a significant improvement in understanding of the robot, comparable with the results obtained using a realtime display. We also find that vocalisation has no significant effect on participants emotional response, though it may slightly increase positive feelings about the robot.We discuss the relative merits of visual and vocalised transparency mechanisms, and suggest possible applications.

Original language	English
Number of pages	6
Publication status	Published - 1 Sep 2017
Event	26th IEEE International Symposium on Robot and Human Interactive Communication (Ro-Man) Workshop on Agent Transparency for Human-Autonomy Teaming Effectiveness - Lisbon, Portugal Duration: 1 Sep 2017 → 1 Sep 2017 https://sites.google.com/view/roman17transparencywkp

Conference

Conference	26th IEEE International Symposium on Robot and Human Interactive Communication (Ro-Man) Workshop on Agent Transparency for Human-Autonomy Teaming Effectiveness
Abbreviated title	RO-MAN2017 Workshop on Agent Transparency for Human-Autonomy Teaming Effectiveness
Country	Portugal
City	Lisbon
Period	1/09/17 → 1/09/17
Internet address	https://sites.google.com/view/roman17transparencywkp

Access to Document

muttering-robotSubmitted manuscript, 2.15 MB

Fingerprint Dive into the research topics of 'The Muttering Robot: Improving Robot Transparency Though Vocalisation of Reactive Plan Execution'. Together they form a unique fingerprint.

Cite this

The Muttering Robot: Improving Robot Transparency Though Vocalisation of Reactive Plan Execution. / Wortham, Robert H; Rogers, Vivienne.

2017. Paper presented at 26th IEEE International Symposium on Robot and Human Interactive Communication (Ro-Man) Workshop on Agent Transparency for Human-Autonomy Teaming Effectiveness, Lisbon, Portugal.

Research output: Contribution to conference › Paper

@conference{4d1f8369ef3e437cae2619e221494e4e,

title = "The Muttering Robot: Improving Robot Transparency Though Vocalisation of Reactive Plan Execution",

abstract = "Transparency is an important design consideration for all intelligent autonomous systems. Previous work shows that a real-time visual display of a robot{\textquoteright}s decision making produces significantly better understanding of that robot{\textquoteright}s intelligence. We investigate vocalisation of behaviour selection as a possible alternative solution for situations where a visual display of decision making is either impractical or impossible. In initial experiments we find that vocalisation is associated with a significant improvement in understanding of the robot, comparable with the results obtained using a realtime display. We also find that vocalisation has no significant effect on participants emotional response, though it may slightly increase positive feelings about the robot.We discuss the relative merits of visual and vocalised transparency mechanisms, and suggest possible applications.",

author = "Wortham, {Robert H} and Vivienne Rogers",

year = "2017",

month = sep,

day = "1",

language = "English",

note = "26th IEEE International Symposium on Robot and Human Interactive Communication (Ro-Man) Workshop on Agent Transparency for Human-Autonomy Teaming Effectiveness, RO-MAN2017 Workshop on Agent Transparency for Human-Autonomy Teaming Effectiveness ; Conference date: 01-09-2017 Through 01-09-2017",

url = "https://sites.google.com/view/roman17transparencywkp",

}

TY - CONF

T1 - The Muttering Robot: Improving Robot Transparency Though Vocalisation of Reactive Plan Execution

AU - Wortham, Robert H

AU - Rogers, Vivienne

PY - 2017/9/1

Y1 - 2017/9/1

N2 - Transparency is an important design consideration for all intelligent autonomous systems. Previous work shows that a real-time visual display of a robot’s decision making produces significantly better understanding of that robot’s intelligence. We investigate vocalisation of behaviour selection as a possible alternative solution for situations where a visual display of decision making is either impractical or impossible. In initial experiments we find that vocalisation is associated with a significant improvement in understanding of the robot, comparable with the results obtained using a realtime display. We also find that vocalisation has no significant effect on participants emotional response, though it may slightly increase positive feelings about the robot.We discuss the relative merits of visual and vocalised transparency mechanisms, and suggest possible applications.

AB - Transparency is an important design consideration for all intelligent autonomous systems. Previous work shows that a real-time visual display of a robot’s decision making produces significantly better understanding of that robot’s intelligence. We investigate vocalisation of behaviour selection as a possible alternative solution for situations where a visual display of decision making is either impractical or impossible. In initial experiments we find that vocalisation is associated with a significant improvement in understanding of the robot, comparable with the results obtained using a realtime display. We also find that vocalisation has no significant effect on participants emotional response, though it may slightly increase positive feelings about the robot.We discuss the relative merits of visual and vocalised transparency mechanisms, and suggest possible applications.

M3 - Paper

T2 - 26th IEEE International Symposium on Robot and Human Interactive Communication (Ro-Man) Workshop on Agent Transparency for Human-Autonomy Teaming Effectiveness

Y2 - 1 September 2017 through 1 September 2017

ER -