Testing Autonomous Robot Control Software Using Procedural Content Generation

James Arnold; Rob Alexander

doi:10.1007/978-3-642-40793-2_4

Testing Autonomous Robot Control Software Using Procedural Content Generation

James Arnold, Rob Alexander

Computer Science

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

Abstract

We present a novel approach for reducing manual effort when testing autonomous robot control algorithms. We use procedural content generation, as developed for the film and video game industries, to create a diverse range of test situations. We execute these in the Player/Stage robot simulator and automatically rate them for their safety significance using an event-based scoring system. Situations exhibiting dangerous behaviour will score highly, and are thus flagged for the attention of a safety engineer. This process removes the time-consuming tasks of hand-crafting and monitoring situations while testing an autonomous robot control algorithm. We present a case study of the proposed approach – we generated 500 randomised situations, and our prototype tool simulated and rated them. We have analysed the three highest rated situations in depth, and this analysis revealed weaknesses in the smoothed nearness-diagram control algorithm.

Original language	English
Title of host publication	Computer Safety, Reliability, and Security
Publisher	Springer
Pages	33-44
Number of pages	12
Volume	8153 LNCS
ISBN (Print)	978-3-642-40793-2
DOIs	https://doi.org/10.1007/978-3-642-40793-2_4
Publication status	Published - 2013
Event	32nd International Conference on Computer Safety, Reliability and Security (SAFECOMP 2013) - Toulouse, France Duration: 24 Sept 2013 → 27 Sept 2013

Publication series

Name	Lecture Notes in Computer Science
Volume	8153
ISSN (Print)	0302-9743

Conference

Conference	32nd International Conference on Computer Safety, Reliability and Security (SAFECOMP 2013)
Country/Territory	France
City	Toulouse
Period	24/09/13 → 27/09/13

Bibliographical note

© 2013, Springer-Verlag Berlin Heidelberg. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details.

Access to Document

10.1007/978-3-642-40793-2_4

Arnold_Testing_Autonomous_Procedural draft v8 camera_ready
© 2013, Springer-Verlag Berlin Heidelberg. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details.
Accepted author manuscript, 469 KBLicence: Unspecified

http://link.springer.com/chapter/10.1007/978-3-642-40793-2_4

Cite this

@inproceedings{b900dd21077f4390981d51de45c3df75,

title = "Testing Autonomous Robot Control Software Using Procedural Content Generation",

abstract = "We present a novel approach for reducing manual effort when testing autonomous robot control algorithms. We use procedural content generation, as developed for the film and video game industries, to create a diverse range of test situations. We execute these in the Player/Stage robot simulator and automatically rate them for their safety significance using an event-based scoring system. Situations exhibiting dangerous behaviour will score highly, and are thus flagged for the attention of a safety engineer. This process removes the time-consuming tasks of hand-crafting and monitoring situations while testing an autonomous robot control algorithm. We present a case study of the proposed approach – we generated 500 randomised situations, and our prototype tool simulated and rated them. We have analysed the three highest rated situations in depth, and this analysis revealed weaknesses in the smoothed nearness-diagram control algorithm.",

author = "James Arnold and Rob Alexander",

note = "{\textcopyright} 2013, Springer-Verlag Berlin Heidelberg. This is an author-produced version of the published paper. Uploaded in accordance with the publisher{\textquoteright}s self-archiving policy. Further copying may not be permitted; contact the publisher for details.; 32nd International Conference on Computer Safety, Reliability and Security (SAFECOMP 2013) ; Conference date: 24-09-2013 Through 27-09-2013",

year = "2013",

doi = "10.1007/978-3-642-40793-2_4",

language = "English",

isbn = "978-3-642-40793-2",

volume = "8153 LNCS",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "33--44",

booktitle = "Computer Safety, Reliability, and Security",

address = "Germany",

}

Arnold, J & Alexander, R 2013, Testing Autonomous Robot Control Software Using Procedural Content Generation. in Computer Safety, Reliability, and Security. vol. 8153 LNCS, Lecture Notes in Computer Science, vol. 8153, Springer, pp. 33-44, 32nd International Conference on Computer Safety, Reliability and Security (SAFECOMP 2013), Toulouse, France, 24/09/13. https://doi.org/10.1007/978-3-642-40793-2_4

TY - GEN

T1 - Testing Autonomous Robot Control Software Using Procedural Content Generation

AU - Arnold, James

AU - Alexander, Rob

N1 - © 2013, Springer-Verlag Berlin Heidelberg. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details.

PY - 2013

Y1 - 2013

N2 - We present a novel approach for reducing manual effort when testing autonomous robot control algorithms. We use procedural content generation, as developed for the film and video game industries, to create a diverse range of test situations. We execute these in the Player/Stage robot simulator and automatically rate them for their safety significance using an event-based scoring system. Situations exhibiting dangerous behaviour will score highly, and are thus flagged for the attention of a safety engineer. This process removes the time-consuming tasks of hand-crafting and monitoring situations while testing an autonomous robot control algorithm. We present a case study of the proposed approach – we generated 500 randomised situations, and our prototype tool simulated and rated them. We have analysed the three highest rated situations in depth, and this analysis revealed weaknesses in the smoothed nearness-diagram control algorithm.

AB - We present a novel approach for reducing manual effort when testing autonomous robot control algorithms. We use procedural content generation, as developed for the film and video game industries, to create a diverse range of test situations. We execute these in the Player/Stage robot simulator and automatically rate them for their safety significance using an event-based scoring system. Situations exhibiting dangerous behaviour will score highly, and are thus flagged for the attention of a safety engineer. This process removes the time-consuming tasks of hand-crafting and monitoring situations while testing an autonomous robot control algorithm. We present a case study of the proposed approach – we generated 500 randomised situations, and our prototype tool simulated and rated them. We have analysed the three highest rated situations in depth, and this analysis revealed weaknesses in the smoothed nearness-diagram control algorithm.

U2 - 10.1007/978-3-642-40793-2_4

DO - 10.1007/978-3-642-40793-2_4

M3 - Conference contribution

SN - 978-3-642-40793-2

VL - 8153 LNCS

T3 - Lecture Notes in Computer Science

SP - 33

EP - 44

BT - Computer Safety, Reliability, and Security

PB - Springer

T2 - 32nd International Conference on Computer Safety, Reliability and Security (SAFECOMP 2013)

Y2 - 24 September 2013 through 27 September 2013

ER -