What are autonomous airfield systems?

Systems that sense conditions, decide within approved rules and carry out routine actions on their own — while people supervise and can always override.

AUTONOMOUS AIRFIELD SYSTEMS · ROUTINE ACTIONS WITHIN APPROVED LIMITS SYSTEM ACTS ON ROUTINE · PEOPLE KEEP CONTROL · ALWAYS OVERRIDABLE 1 SENSE Equipment status Weather and visibility Airfield conditions STAGE: sense 2 DECIDE Approved rules apply Choice within set limits Unsure means safe state STAGE: decide 3 ACT Select a lighting set-up Raise a ranked alarm Send an inspection check STAGE: act 4 OVERSEE People supervise Can override at any time Every action logged STAGE: oversight LOGGED OUTCOMES ARE REVIEWED, THEN THE RULES ARE IMPROVED WELL SUITED TO ROUTINE DECISIONS AT SPEED Repeatable actions done quickly and consistently LIMITS SAFETY CASE · OVERRIDE · CYBER Safety-critical changes need approval and a human decision USED WITHIN THE APPROVED SAFETY CASE AND PROCEDURES · NOT A REPLACEMENT FOR PEOPLE SCHEMATIC · SIMPLIFIED · NOT TO SCALE · FEATURES AND METHODS VARY BY SUPPLIER
autonomy stage
feedback loop
limits and human decision
The Fact Future technology

An autonomous airfield system senses conditions, decides within rules set in advance and carries out routine actions without a person starting each one, such as choosing a lighting configuration, ranking alarms or sending an automated inspection to a flagged light.

It does repeatable work quickly and consistently, so people can focus on judgement. But it works only inside approved limits, people can override it at any time, and every action is logged. Faulty data, software errors and cyber-security are real risks, so its behaviour is tested and approved through the aerodrome’s safety management process. When unsure, it falls back to a safe state and alerts a person.

  1. Sense. Collect equipment status, weather and airfield conditions.
  2. Decide. Apply the approved rules to choose a routine action within set limits.
  3. Act. Carry out the action, such as selecting a lighting set-up or raising a ranked alarm.
  4. Oversee. People supervise, can override at any time, and every action is logged.
  5. Fall back. If data is missing or the situation is unclear, go to a safe defined state and alert a person.
  6. Review. Logged outcomes are reviewed and the rules are improved under change control.
Purpose Take over repeatable routine decisions and actions, quickly and consistently
Core job Sense, decide within approved rules, act, and log; people stay in charge
Needs Reliable data, approved rules, an override, a safe fallback state and secure communication
Key idea The system handles routine work; people hold the authority and the responsibility
Limits Bad or missing data, software faults, cyber-security, over-reliance, approval effort
Reference ICAO Annex 14 and Annex 19; the national regulator’s approval; the supplier’s documentation
Autonomous system

Senses and decides within approved rules, acts on routine matters, and logs everything, with people supervising and able to override.

Manual operation

A person makes and carries out each decision. Consistency and speed depend on the person on duty.

Schematic — simplified for clarity. Capabilities and methods vary by supplier and site, and many are still emerging. Any autonomous function must be approved through the aerodrome’s safety management process under ICAO Annex 14, Annex 19, the national regulator and the aerodrome’s approved procedures.
Entry 19 · Sustainable AGL Entry 21 · Future airport lighting

Frequently Asked Questions

Q1What are autonomous airfield systems in airfield ground lighting?

Systems that sense conditions on the airfield, decide within rules set in advance and carry out routine actions without a person starting each one. Examples include selecting a lighting configuration for the runway in use or sending an automated inspection vehicle to check a flagged light.

Q2Is an autonomous system the same as an automatic one?

The terms overlap. An automatic function follows a fixed rule, such as switching on at a set light level. An autonomous system adds sensing and decision-making within approved limits, so it can choose between actions. Both must stay inside their approved design.

Q3What decisions can it make?

Routine, repeatable ones inside approved limits, such as selecting a brightness step, switching a configured lighting pattern, raising a ranked alarm or scheduling a check. Safety-critical changes stay with qualified people unless the regulator has approved otherwise, and ATC keeps authority over which runway lighting is in use and at what intensity step, as the aerodrome’s procedures set.

Q4Where does human oversight come in?

People set the rules, supervise the system, can override it at any time and review what it did. Every action is logged. If the system is unsure, loses data or detects a fault, it should fall back to a safe, defined state and alert a person.

Q5What are the limits and risks?

Wrong or missing sensor data, software faults, cyber-security and over-reliance on the system. Its behaviour must be tested, its limits known, and it must be approved through the aerodrome’s safety management process before it is used.

Q6Does it replace engineers and operators?

No. It takes over repeatable routine work. Inspection, testing and maintenance still follow ICAO Annex 14, the national regulator and the aerodrome’s approved procedures, and a person remains responsible for safety-critical decisions.

Precision AGL Academy

See It. Understand It. Then Learn How to Engineer It.

Recognising an AGL system visually is the first step. The next step is knowing how to design, install, test, commission and maintain them correctly.

Build Practical AGL Engineering Skills

Go deeper with structured training from Precision AGL Academy, covering:

AGL Fundamentals Design & Electrical Engineering Approach Lighting Photometry Installation & Commissioning Maintenance & Troubleshooting

Learn how each light, sign and circuit works as part of a complete airport lighting system, not just as an isolated diagram.

See. Understand. Apply. Engineer.