Want to know more?

Other case studies

Adaptive optics is a technology that allows a deformable mirror to be used to correct optical distortion due to atmospheric turbulence in real time and is of critical importance in ground-based telescopes.

**The Challenge**

Mitigating atmospheric turbulence requires the design of a decentralized system to control the deformation of the telescope mirror, ensuring stability and performance in terms of response time and accuracy.

**The Solution**

We applied a data-driven approach that uses frequency profiles of turbulence and vibration directly obtained from experimental data. In this way it is possible to obtain a real-time response prediction and optimize the telescope mirror control system.

**Results and Benefits**

The solution allows a clear improvement of the telescope performance, thanks to the real-time stabilization of the mirrors even in adverse weather conditions.

Data-driven control: how to take advantage of experimental data and frequency analysis to optimize a system in real time. Find out more!

Data-driven Control System

Leverage real-time data and forecasts to optimize control system decisions

Model Predictive Control

Real time correction for optical distortion of deformable mirrors

The combination of optimization and optimal control techniques, which DEIX is able to offer, is fundamental in all of those contexts in which the decision-making problem to be solved is **dynamic**, i.e. it requires a **planning of decisions over time**. For example, in the management and control algorithms necessary for the correct operation of an automation system or in decision support in management and logistics. In fact, the introduction of a feedback mechanism in the decision-making process allows the proposed solution to **adapt** in a natural way **to all possible variations** from the expected behavior.

Control and decision optimization combines **predictive mathematical models** (describing the objectives and constraints of the decision problem and its evolution over time) with **learning from data** and **reinforcement learning** techniques if the models are not known analytically. 

In the context of complex learning, control, decision and optimization problems, knowledge extraction from heterogeneous data and **sensors** plays a key role. In this area, Deix provides **sensor & data fusion** solutions that combine mathematical models with statistical inference techniques, learning from data and artificial intelligence. 

These solutions enable the creation of **virtual sensors**, i.e., algorithms that can provide accurate real-time estimates of quantities of interest beyond those that can be directly measured.

This type of approach finds a natural application in the implementation of **Digital Twins** of processes and products.

Sensor Data Fusion, Optimal control & Digital Twin: we create algorithms for processes optimization in order to better support business decisions.

Data-driven Control System

Other case studies

Real Time Object Tracking

Data Augmentation on Satellite Images