Increasing safety by combining multiple declarative rules in robotic perception systems

Johann Thor Mogensen Ingibergsson, Dirk Kraft, Ulrik Pagh Schultz*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

Advanced cyber-physical systems such as mobile, networked robots are increasingly finding use in everyday society. A critical aspect of mobile robotics is the ability to react to a dynamically changing environment, which imposes significant requirements on the robot perception system. The perception system is key to maintaining safe navigation and operation for the robot and is often considered a safety-critical aspect of the system as a whole. To allow the system to operate in a public area the perception system thus has to be certified. The key issue that we address is how to have safety-compliant systems while keeping implementation transparency high and complexity low. In this paper we present an evaluation of different methods for modelling combinations of simple explicit computer vision rules designed to increase the trustworthiness of the perception system. We utilise the best-performing method, focusing on keeping the models of the perception pipeline transparent and understandable. We find that it is possible to improve the safety of the system with some performance cost, depending on the acceptable risk level.

Original languageEnglish
Title of host publicationCyber Physical Systems. Design, Modeling, and Evaluation : 7th International Workshop, CyPhy 2017, Revised Selected Papers
EditorsRoger Chamberlain, Walid Taha, Martin Törngren
PublisherSpringer VS
Publication date13. Apr 2019
Pages43-60
ISBN (Print)9783030179090
ISBN (Electronic)978-3-030-17910-6
DOIs
Publication statusPublished - 13. Apr 2019
Event7th International Workshop on Design, Modeling, and Evaluation of Cyber Physical Systems, CyPhy 2017 - Seoul, Korea, Republic of
Duration: 15. Oct 201720. Oct 2017

Conference

Conference7th International Workshop on Design, Modeling, and Evaluation of Cyber Physical Systems, CyPhy 2017
CountryKorea, Republic of
CitySeoul
Period15/10/201720/10/2017
SeriesLecture Notes in Computer Science
Volume11267
ISSN0302-9743

Fingerprint

Robotics
Robots
Transparency
Computer vision
Navigation
Pipelines
Costs
Cyber Physical System

Keywords

  • Computer vision
  • Functional safety
  • Robotics
  • Safety

Cite this

Ingibergsson, J. T. M., Kraft, D., & Schultz, U. P. (2019). Increasing safety by combining multiple declarative rules in robotic perception systems. In R. Chamberlain, W. Taha, & M. Törngren (Eds.), Cyber Physical Systems. Design, Modeling, and Evaluation: 7th International Workshop, CyPhy 2017, Revised Selected Papers (pp. 43-60). Springer VS. Lecture Notes in Computer Science, Vol.. 11267 https://doi.org/10.1007/978-3-030-17910-6_4
Ingibergsson, Johann Thor Mogensen ; Kraft, Dirk ; Schultz, Ulrik Pagh. / Increasing safety by combining multiple declarative rules in robotic perception systems. Cyber Physical Systems. Design, Modeling, and Evaluation: 7th International Workshop, CyPhy 2017, Revised Selected Papers. editor / Roger Chamberlain ; Walid Taha ; Martin Törngren. Springer VS, 2019. pp. 43-60 (Lecture Notes in Computer Science, Vol. 11267).
@inproceedings{fe3060518e2e437f98a67903dcbed6c2,
title = "Increasing safety by combining multiple declarative rules in robotic perception systems",
abstract = "Advanced cyber-physical systems such as mobile, networked robots are increasingly finding use in everyday society. A critical aspect of mobile robotics is the ability to react to a dynamically changing environment, which imposes significant requirements on the robot perception system. The perception system is key to maintaining safe navigation and operation for the robot and is often considered a safety-critical aspect of the system as a whole. To allow the system to operate in a public area the perception system thus has to be certified. The key issue that we address is how to have safety-compliant systems while keeping implementation transparency high and complexity low. In this paper we present an evaluation of different methods for modelling combinations of simple explicit computer vision rules designed to increase the trustworthiness of the perception system. We utilise the best-performing method, focusing on keeping the models of the perception pipeline transparent and understandable. We find that it is possible to improve the safety of the system with some performance cost, depending on the acceptable risk level.",
keywords = "Computer vision, Functional safety, Robotics, Safety",
author = "Ingibergsson, {Johann Thor Mogensen} and Dirk Kraft and Schultz, {Ulrik Pagh}",
year = "2019",
month = "4",
day = "13",
doi = "10.1007/978-3-030-17910-6_4",
language = "English",
isbn = "9783030179090",
series = "Lecture Notes in Computer Science",
publisher = "Springer VS",
pages = "43--60",
editor = "Roger Chamberlain and Walid Taha and Martin T{\"o}rngren",
booktitle = "Cyber Physical Systems. Design, Modeling, and Evaluation",

}

Ingibergsson, JTM, Kraft, D & Schultz, UP 2019, Increasing safety by combining multiple declarative rules in robotic perception systems. in R Chamberlain, W Taha & M Törngren (eds), Cyber Physical Systems. Design, Modeling, and Evaluation: 7th International Workshop, CyPhy 2017, Revised Selected Papers. Springer VS, Lecture Notes in Computer Science, vol. 11267, pp. 43-60, 7th International Workshop on Design, Modeling, and Evaluation of Cyber Physical Systems, CyPhy 2017, Seoul, Korea, Republic of, 15/10/2017. https://doi.org/10.1007/978-3-030-17910-6_4

Increasing safety by combining multiple declarative rules in robotic perception systems. / Ingibergsson, Johann Thor Mogensen; Kraft, Dirk; Schultz, Ulrik Pagh.

Cyber Physical Systems. Design, Modeling, and Evaluation: 7th International Workshop, CyPhy 2017, Revised Selected Papers. ed. / Roger Chamberlain; Walid Taha; Martin Törngren. Springer VS, 2019. p. 43-60 (Lecture Notes in Computer Science, Vol. 11267).

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - Increasing safety by combining multiple declarative rules in robotic perception systems

AU - Ingibergsson, Johann Thor Mogensen

AU - Kraft, Dirk

AU - Schultz, Ulrik Pagh

PY - 2019/4/13

Y1 - 2019/4/13

N2 - Advanced cyber-physical systems such as mobile, networked robots are increasingly finding use in everyday society. A critical aspect of mobile robotics is the ability to react to a dynamically changing environment, which imposes significant requirements on the robot perception system. The perception system is key to maintaining safe navigation and operation for the robot and is often considered a safety-critical aspect of the system as a whole. To allow the system to operate in a public area the perception system thus has to be certified. The key issue that we address is how to have safety-compliant systems while keeping implementation transparency high and complexity low. In this paper we present an evaluation of different methods for modelling combinations of simple explicit computer vision rules designed to increase the trustworthiness of the perception system. We utilise the best-performing method, focusing on keeping the models of the perception pipeline transparent and understandable. We find that it is possible to improve the safety of the system with some performance cost, depending on the acceptable risk level.

AB - Advanced cyber-physical systems such as mobile, networked robots are increasingly finding use in everyday society. A critical aspect of mobile robotics is the ability to react to a dynamically changing environment, which imposes significant requirements on the robot perception system. The perception system is key to maintaining safe navigation and operation for the robot and is often considered a safety-critical aspect of the system as a whole. To allow the system to operate in a public area the perception system thus has to be certified. The key issue that we address is how to have safety-compliant systems while keeping implementation transparency high and complexity low. In this paper we present an evaluation of different methods for modelling combinations of simple explicit computer vision rules designed to increase the trustworthiness of the perception system. We utilise the best-performing method, focusing on keeping the models of the perception pipeline transparent and understandable. We find that it is possible to improve the safety of the system with some performance cost, depending on the acceptable risk level.

KW - Computer vision

KW - Functional safety

KW - Robotics

KW - Safety

U2 - 10.1007/978-3-030-17910-6_4

DO - 10.1007/978-3-030-17910-6_4

M3 - Article in proceedings

AN - SCOPUS:85065047041

SN - 9783030179090

T3 - Lecture Notes in Computer Science

SP - 43

EP - 60

BT - Cyber Physical Systems. Design, Modeling, and Evaluation

A2 - Chamberlain, Roger

A2 - Taha, Walid

A2 - Törngren, Martin

PB - Springer VS

ER -

Ingibergsson JTM, Kraft D, Schultz UP. Increasing safety by combining multiple declarative rules in robotic perception systems. In Chamberlain R, Taha W, Törngren M, editors, Cyber Physical Systems. Design, Modeling, and Evaluation: 7th International Workshop, CyPhy 2017, Revised Selected Papers. Springer VS. 2019. p. 43-60. (Lecture Notes in Computer Science, Vol. 11267). https://doi.org/10.1007/978-3-030-17910-6_4