Inherently privacy-preserving vision for trustworthy autonomous systems: Needs and solutions
Vision is an effective sensor for robotics from which we can derive rich information about the environment: the geometry and semantics of the scene, as well as the age, identity, and activity of humans within that scene. This raises important questions about the reach, lifespan, and misuse of this i...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-03-01
|
| Series: | Journal of Responsible Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666659624000052 |
| _version_ | 1797262856825077760 |
|---|---|
| author | Adam K. Taras Niko Sünderhauf Peter Corke Donald G. Dansereau |
| author_facet | Adam K. Taras Niko Sünderhauf Peter Corke Donald G. Dansereau |
| author_sort | Adam K. Taras |
| collection | DOAJ |
| description | Vision is an effective sensor for robotics from which we can derive rich information about the environment: the geometry and semantics of the scene, as well as the age, identity, and activity of humans within that scene. This raises important questions about the reach, lifespan, and misuse of this information. This paper is a call to action to consider privacy in robotic vision. We propose a specific form of inherent privacy preservation in which no images are captured or could be reconstructed by an attacker, even with full remote access. We present a set of principles by which such systems could be designed, employing data-destroying operations and obfuscation in the optical and analogue domains. These cameras never see a full scene. Our localisation case study demonstrates in simulation four implementations that all fulfil this task. The design space of such systems is vast despite the constraints of optical-analogue processing. We hope to inspire future works that expand the range of applications open to sighted robotic systems. |
| first_indexed | 2024-03-07T18:35:18Z |
| format | Article |
| id | doaj.art-775539d3053845eda0c43ad1e1fab18e |
| institution | Directory Open Access Journal |
| issn | 2666-6596 |
| language | English |
| last_indexed | 2024-04-25T00:03:46Z |
| publishDate | 2024-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Responsible Technology |
| spelling | doaj.art-775539d3053845eda0c43ad1e1fab18e2024-03-14T06:16:18ZengElsevierJournal of Responsible Technology2666-65962024-03-0117100079Inherently privacy-preserving vision for trustworthy autonomous systems: Needs and solutionsAdam K. Taras0Niko Sünderhauf1Peter Corke2Donald G. Dansereau3Australian Centre For Robotics, School of Aerospace, Mechanical and Mechatronic Engineering, The University of Sydney, 2006, NSW, AustraliaQueensland University of Technology (QUT), Centre for Robotics, Brisbane, 4001, QLD, AustraliaQueensland University of Technology (QUT), Centre for Robotics, Brisbane, 4001, QLD, AustraliaAustralian Centre For Robotics, School of Aerospace, Mechanical and Mechatronic Engineering, The University of Sydney, 2006, NSW, Australia; Corresponding author.Vision is an effective sensor for robotics from which we can derive rich information about the environment: the geometry and semantics of the scene, as well as the age, identity, and activity of humans within that scene. This raises important questions about the reach, lifespan, and misuse of this information. This paper is a call to action to consider privacy in robotic vision. We propose a specific form of inherent privacy preservation in which no images are captured or could be reconstructed by an attacker, even with full remote access. We present a set of principles by which such systems could be designed, employing data-destroying operations and obfuscation in the optical and analogue domains. These cameras never see a full scene. Our localisation case study demonstrates in simulation four implementations that all fulfil this task. The design space of such systems is vast despite the constraints of optical-analogue processing. We hope to inspire future works that expand the range of applications open to sighted robotic systems.http://www.sciencedirect.com/science/article/pii/S2666659624000052Privacy-preserving visionOptical computingRobotic imagingLocalisation |
| spellingShingle | Adam K. Taras Niko Sünderhauf Peter Corke Donald G. Dansereau Inherently privacy-preserving vision for trustworthy autonomous systems: Needs and solutions Journal of Responsible Technology Privacy-preserving vision Optical computing Robotic imaging Localisation |
| title | Inherently privacy-preserving vision for trustworthy autonomous systems: Needs and solutions |
| title_full | Inherently privacy-preserving vision for trustworthy autonomous systems: Needs and solutions |
| title_fullStr | Inherently privacy-preserving vision for trustworthy autonomous systems: Needs and solutions |
| title_full_unstemmed | Inherently privacy-preserving vision for trustworthy autonomous systems: Needs and solutions |
| title_short | Inherently privacy-preserving vision for trustworthy autonomous systems: Needs and solutions |
| title_sort | inherently privacy preserving vision for trustworthy autonomous systems needs and solutions |
| topic | Privacy-preserving vision Optical computing Robotic imaging Localisation |
| url | http://www.sciencedirect.com/science/article/pii/S2666659624000052 |
| work_keys_str_mv | AT adamktaras inherentlyprivacypreservingvisionfortrustworthyautonomoussystemsneedsandsolutions AT nikosunderhauf inherentlyprivacypreservingvisionfortrustworthyautonomoussystemsneedsandsolutions AT petercorke inherentlyprivacypreservingvisionfortrustworthyautonomoussystemsneedsandsolutions AT donaldgdansereau inherentlyprivacypreservingvisionfortrustworthyautonomoussystemsneedsandsolutions |