Quality
Set observable service acceptance criteria.
Deployment evaluation · 13
Measure useful task outcome
Use service-specific quality and completion measures with every attempt in the denominator.
Evidence statusService decision framework · site and user validation requiredLast reviewed: 14 August 2026
13
FUURAA thesis
A fair metric counts what users receive, what staff repair and what the system abandons.
Engineering map
Turn the title into engineering objects that can be observed, measured and reviewed.
Each layer states the boundary to establish and the evidence needed for the next decision.
Completeness
Count success, partial success, retry, intervention and damage.
Human impact
Measure waiting, workload, dignity and accessibility.
Verification questions
Write the questions first, then decide whether a demo, test, pilot or operating record can answer them.
Each question needs an object, conditions, denominator, threshold and accountable decision owner.
- 01
Does the metric reflect recipient need?
- 02
Are all attempts included?
- 03
Is manual finishing counted?
- 04
What threshold supports expansion?
Evidence to preserve
Enable the next reader to reconstruct conditions, results, failures and the decision.
A conclusion alone loses reviewability; raw records, configuration and exclusions matter too.
- 01
Evidence package 1
Outcome specification
- 02
Evidence package 2
Attempt-level dataset
- 03
Evidence package 3
Decision threshold record
Scope boundary
State what this evidence still cannot be generalised to.
- 01
Selected successful runs do not establish outcomes in the buyer's service.
- 02
This is an engineering reading and decision framework; it does not replace application-specific risk assessment, conformity work, procurement acceptance or professional advice.
Sources and evidence status
Read standards scope, measurement evidence and application conclusions separately.
Source dates and review status remain visible; external sources open in a new tab.
01
ISO · 2024-01
↗02ISO 18646-2:2024 — Navigation performance of service robots
Defines methods for pose accuracy, obstacle response, path deviation, narrow passage and mapping accuracy.
ISO · 2023-11
↗ISO 31101:2023 — Safety management for services provided by service robots
Addresses safety management for service-robot applications in human spaces with trained and untrained people.