Commissioned artefact
Task suite and policy comparison.
Robot policy benchmarking
Evaluate task success and robustness within a defined physical testing scope.
Commission this programmeSpecialist engineering programme
Evaluate task success and robustness within a defined physical testing scope.
A defined contribution.
Acceptance focus
Assess performance across representative starting states, disturbances and failures rather than one polished demonstration.
The operating task
Evaluate task success and robustness within a defined physical testing scope. Observation, action and task completion are considered together within the selected embodiment and environment.
Softinator's contribution
Define a task-testing scope that makes policy success and robustness interpretable. The commissioned output includes task suite and policy comparison.
Acceptance in use
Assess performance across representative starting states, disturbances and failures rather than one polished demonstration. The engagement defines the baseline, task scope and evidence used to assess the resulting contribution.
Bring the next
requirement.