23 stycznia 2026
The problem: static automation vs. dynamic passenger flow
During peak hours, an airport has its own rhythm. Some gates are full of passengers waiting to board, while others have just emptied after departure or are waiting for the next flight. Passenger traffic is high, but uneven – and it can change from minute to minute.
Systems such as HVAC, meaning Heating, Ventilation and Air Conditioning, often operate continuously, based on schedules or fixed settings. Whether there are dozens of people in a given zone or no one at all for a certain period of time, the air conditioning system maintains predefined parameters.
The result is predictable: unnecessary cooling, high energy consumption, and limited flexibility.
Our client wanted to solve this problem and came to us with a specific question: how can air conditioning be connected to the actual use of space without rebuilding the entire system?
The solution: Edge AI + thermal vision + software-defined automation
Instead of replacing the existing infrastructure, we focused on adding the missing layer of context. The goal was to introduce a system that could answer one key question in real time: what is actually happening in a given space?
The scope of work covered the full process – from data acquisition to its use in automation:
- selection and testing of thermal vision and RGB cameras in real airport conditions,
- development of an Edge AI model for detecting, tracking, and counting people across different zones, such as airport gates,
- design of decision logic combining occupancy data with temperature readings,
- integration with the client’s existing automation drives controlling the HVAC system,
- implementation of a software-defined automation approach, enabling flexible management of control logic,
- configuration of communication between the Edge AI layer and the automation system.
This is a practical example of physical AI – artificial intelligence that does not only analyze data, but also supports automated decisions in the physical environment, such as controlling cooling, ventilation, or energy usage.
How does it work in practice?
The core idea behind the solution is simple: air conditioning should not be controlled only by time, but by what is actually happening in the space.
The system makes decisions based on two signals: the number of people in a given zone and the current temperature. Based on this data, HVAC control logic is triggered automatically.
Example scenarios:
- the gate is empty – air conditioning is turned off or switched to a reduced operating mode,
- passengers enter the zone – the system automatically starts cooling,
- the temperature exceeds a defined threshold – air conditioning is activated regardless of the number of people.
Business impact
The solution enables:
- real reduction of energy consumption in low-occupancy zones,
- no negative impact on passenger comfort, as the system works in the background and reacts automatically,
- better use of existing infrastructure without the need for full replacement,
- further development of the logic, for example by adding passenger flow prediction.
The ready demo, similar to our Edge AI and thermal vision solution for a cattle farm, was presented together with our client at Hannover Messe 2026.
What comes next?
This approach works best in dynamic environments – places where the number of people and space conditions change over time and are difficult to predict.
It is especially useful when energy costs have a direct impact on operations, and when existing automation infrastructure, such as automation drives, can be extended instead of replaced.
The same model can be applied to other environments facing similar challenges at a different scale, including:
- production halls,
- warehouses and logistics centers,
- open-space offices,
- retail facilities.
In each case, the logic remains the same: connect real-world data with the control system and allow decisions to be made automatically, continuously, and based on actual conditions.
Want to build a similar solution?
Do you have an unusual idea or a technical challenge that cannot be solved with an off-the-shelf product? Get in touch with us. We like projects that do not fit into standard frameworks.
Want to build a similar solution?
Do you have an unusual idea or a technical challenge that cannot be solved with an off-the-shelf product? Get in touch with us. We like projects that do not fit into standard frameworks.
Wi-Fi HaLow: The missing link in IoT connectivity
Discover Wi-Fi HaLow – Wi-Fi HaLow is a sub-1 GHz Wi-Fi technology for IoT, offering a range of up to 1 km and low power consumption.
