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

44 Downloads (Pure)

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
Country/TerritoryKorea, Republic of
CitySeoul
Period15/10/201720/10/2017
SeriesLecture Notes in Computer Science
Volume11267
ISSN0302-9743

Keywords

  • Computer vision
  • Functional safety
  • Robotics
  • Safety

Fingerprint

Dive into the research topics of 'Increasing safety by combining multiple declarative rules in robotic perception systems'. Together they form a unique fingerprint.

Cite this