Past review · · Go to the latest review

← Back to all ten traits

Makes decisions onboard

Research drones make navigation decisions onboard. MonoRace adds a competition example, but these tasks do not establish unrestricted autonomy.

Shown in practiceConfidence: Medium

Last reviewed

What we are looking for

Are decisions made onboard without live operator control?

Where this applies

Research drones, including Swift and MonoRace · bounded navigation and racing tasks

What has been observed

What limits this finding

What we still need to know

Independent replication of the same configuration in changing conditions.

What would change our view

A traceable replication or documented failure changes confidence.

What would be enough to confirm it

A physical test must locate decision-making onboard and identify the autonomous task.

How this finding has changed
  1. Shown in practice

    Research drones make navigation decisions onboard. MonoRace adds a competition example, but these tasks do not establish unrestricted autonomy.

    Updated assessment. Added a different team’s race result and limitations from the same A2RL event. Ratings and confidence remain unchanged.

  2. Shown in practice

    Research drones make navigation decisions onboard. MonoRace adds a competition example, but these tasks do not establish unrestricted autonomy.

    Checked again; no change. Reviewed; rating and confidence unchanged. The inspected material does not resolve the remaining gap.

  3. Shown in practice

    Research drones make navigation decisions onboard. MonoRace adds a competition example, but these tasks do not establish unrestricted autonomy.

    Updated assessment. New scoped evidence added; rating and confidence unchanged. Different platforms and limits remain separate.

  4. Shown in practice

    Research drones make navigation decisions onboard, including during a rotor-failure test. These bounded tasks do not establish unrestricted autonomy.

    Updated assessment. Added onboard navigation on the same research configuration used for the rotor-failure test; rating and confidence unchanged.

  5. Shown in practice

    Swift made its own flight decisions on a trained racecourse. This does not establish wider mission autonomy.

    Checked again; no change. Reviewed; the rating and confidence remain unchanged. No qualifying new evidence resolved this parameter’s gap.

  6. Shown in practice

    Swift made its own flight decisions on a trained racecourse. This does not establish wider mission autonomy.

    First review. Initial assessment; no previous cycle for comparison.