Engineering:Operational design domain

From HandWiki

Operational design domain (ODD) is a term for a set of operating conditions for an automated system, often used in the field of autonomous vehicles. These operating conditions include environmental, geographical and time of day constraints, traffic and roadway characteristics. The ODD is used by manufacturers to indicate where their product will operate safely.[1]

The concept of ODD indicates that autonomated systems have limitations and that they should operate within predefined restrictions to ensure safety and performance.[2] Defining an ODD is important for developers and regulators to establish clear expectations and communicate the intended operating conditions of automated systems.

Beyond self-driving cars, ODD is also used for autonomous ships,[3] autonomous trains,[4] agricultural robots,[5] and other robots.

ODD definition by standards

Definition Source
"set of operating conditions under which a given driving automation system ... or feature thereof is specifically designed to function" ISO/TS 14812:2022(en), 3.7.3.2[6]
"operating conditions under which a given automated driving system ... or feature thereof is specifically designed to function, including, but not limited to, environmental, geographical, and time-of-day restrictions, and/or the requisite presence or absence of certain traffic or roadway characteristics" ISO/TR 4804:2020(en), 3.37[7]
"operating conditions under which a given driving automation system or feature thereof is specifically designed to function, including, but not limited to, environmental, geographical, and time-of-day restrictions, and/or the requisite presence or absence of certain traffic or roadway characteristics" ISO 34501:2022(en), 3.26[8]
"specific conditions under which a given driving automation system is designed to function" ISO 21448:2022(en), 3.21[9]
"operating conditions under which a given driving automation system or feature thereof is specifically designed to function" BSI PAS 1883[10]
"set of environments and situations the item is to operate within" ANSI/UL 4600[11]
"environmental, geographic, time-of-day, traffic, infrastructure, weather and other conditions under which an automated driving system is specifically designed to function" Global Forum for Road Traffic Safety (WP.1) resolution on the deployment of highly and fully automated vehicles in road traffic[12]
"For the assessment of the vehicle safety, the vehicle manufacturers should document the [ODD] available on their vehicles and the functionality of the vehicle within the prescribed [ODD]. The [ODD] should describe the specific conditions under which the automated vehicle is intended to drive in the automated mode. The [ODD] should include the following information at a minimum: roadway types; geographic area; speed range; environmental conditions (weather as well as day/night time); and other domain constraints." Revised Framework document on automated/autonomous vehicles (WP.29)[13]
"Operational Design Domain (ODD) of the automated lane keeping system defines the specific operating conditions (e.g. environmental, geographic, time-of-day, traffic, infrastructure, speed range, weather and other conditions) within the boundaries fixed by this regulation under which the automated lane keeping system is designed to operate without any intervention by the driver." UN Regulation No 157 – Uniform provisions concerning the approval of vehicles with regards to Automated Lane Keeping Systems [2021/389][14]

Structure of ODD

A report by US Department of Transportation subdivides an ODD description into six top-level categories and further immediate subcategories.[15] The top-level categories are the physical infrastructure, operational constraints, objects, connectivity, environmental conditions and zones. The physical infrastructure includes subcategories for roadway types, surfaces, edges and geometry. The operational constraints include subcategories for speed limits and traffic conditions. Environmental conditions include weather, illumination, and similar sub-categories. Zones include subcategories like regions, states, school areas, construction sites and similar.

Examples

In 2022, Mercedes-Benz announced a product with a new ODD, which is Level 3 autonomous driving at 130 km/h.[16]

See also

References

  1. Lee, Chung Won; Nayeer, Nasif; Garcia, Danson Evan; Agrawal, Ankur; Liu, Bingbing (October 2020). "Identifying the Operational Design Domain for an Automated Driving System through Assessed Risk". 2020 IEEE Intelligent Vehicles Symposium (IV). pp. 1317–1322. doi:10.1109/IV47402.2020.9304552. ISBN 978-1-7281-6673-5. https://ieeexplore.ieee.org/document/9304552. 
  2. Erz, Jannis; Schütt, Barbara; Braun, Thilo; Guissouma, Houssem; Sax, Eric (April 2022). "Towards an Ontology That Reconciles the Operational Design Domain, Scenario-based Testing, and Automated Vehicle Architectures". 2022 IEEE International Systems Conference (SysCon). pp. 1–8. doi:10.1109/SysCon53536.2022.9773840. ISBN 978-1-6654-3992-3. 
  3. Yamada, Tomoaki; Sato, Makoto; Kuranobu, Rikiya; Watanabe, Ryo; Itoh, Hiroko; Shiokari, Megumi; Yuzui, Tomohiro (1 July 2022). "Evaluation of effectiveness of the STAMP / STPA in risk analysis of autonomous ship systems". Journal of Physics: Conference Series 2311 (1): 012021. doi:10.1088/1742-6596/2311/1/012021. 
  4. Meng, Zicong; Tang, Tao; Wei, Guodong; Yuan, Lei (January 2021). "Analysis of ATO System Operation Scenarios Based on UPPAAL and the Operational Design Domain" (in en). Electronics 10 (4): 503. doi:10.3390/electronics10040503. ISSN 2079-9292. 
  5. Krank, Joshua (2020). "Robo-Crop: The Imminence of Autonomous Technology in Agriculture". Drake Journal of Agricultural Law 25: 473. https://heinonline.org/HOL/LandingPage?handle=hein.journals/dragl25&div=30. 
  6. ISO/TS 14812:2022, Intelligent transport systems — Vocabulary, https://www.iso.org/standard/79779.html 
  7. ISO/TR 4804:2020, Road vehicles — Safety and cybersecurity for automated driving systems — Design, verification and validation, https://www.iso.org/standard/80363.html 
  8. ISO 34501:2022, Road vehicles — Test scenarios for automated driving systems — Vocabulary, https://www.iso.org/standard/78950.html 
  9. ISO 21448:2022, Road vehicles — Safety of the intended functionality, https://www.iso.org/standard/77490.html 
  10. "PAS 1883:2020". BSI Group. https://www.bsigroup.com/globalassets/localfiles/en-gb/cav/pas1883.pdf. 
  11. Peleska, Jan; Haxthausen, Anne E.; Lecomte, Thierry (2022). "Standardisation Considerations for Autonomous Train Control" (in en). Leveraging Applications of Formal Methods, Verification and Validation. Practice. Lecture Notes in Computer Science (Springer Nature Switzerland) 13704: 286–307. doi:10.1007/978-3-031-19762-8_22. ISBN 978-3-031-19761-1. https://link.springer.com/chapter/10.1007/978-3-031-19762-8_22. 
  12. "Resolution on the Deployment of Highly and Fully Automated Vehicles in Road Traffic | UNECE". UNECE. September 2018. https://unece.org/transport/publications/resolution-deployment-highly-and-fully-automated-vehicles-road-traffic. 
  13. "Framework Document for Automated/Autonomous Vehicles (UPDATED) | UNECE". UNECE. February 2022. https://unece.org/info/publications/pub/365097. 
  14. UN Regulation No 157
  15. Thorn, Eric; Kimmel, Shawn C.; Chaka, Michelle (1 September 2018). "A Framework for Automated Driving System Testable Cases and Scenarios" (in English). https://rosap.ntl.bts.gov/view/dot/38824. 
  16. Rocco, Nicolas La (12 August 2022). "Level-3-Fahren mit 130 km/h: Mercedes gestaltet nächste ODD für Drive Pilot aus" (in de). ComputerBase. https://www.computerbase.de/2022-08/level-3-fahren-mit-130-km-h-mercedes-gestaltet-naechste-odd-fuer-drive-pilot-aus/.