Scenarios
Build cases from observation, incidents and user diversity.
Deployment evaluation · 14
Test crowds, children, pets, mobility aids, poor lighting, noise, obstruction and deliberate interference.
FUURAA thesis
Engineering map
Each layer states the boundary to establish and the evidence needed for the next decision.
Build cases from observation, incidents and user diversity.
Specify safeguards, repetitions, stop criteria and observers.
Turn findings into route, interface and staffing changes.
Verification questions
Each question needs an object, conditions, denominator, threshold and accountable decision owner.
Which real encounters generated cases?
Were vulnerable users represented safely?
How are near misses recorded?
Which failures change deployment?
Evidence to preserve
A conclusion alone loses reviewability; raw records, configuration and exclusions matter too.
Scenario matrix
Stops and near-miss record
Corrective action history
Scope boundary
A short pilot with staff nearby can suppress behaviours and recovery delays.
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
Source dates and review status remain visible; external sources open in a new tab.
Addresses safety management for service-robot applications in human spaces with trained and untrained people.
Describes test methods supporting ISO 13482 and requires test selection and parameters to follow risk assessment.