Litcius/Paper detail

Experimental phase control of a 100 laser beam array with quasi-reinforcement learning of a neural network in an error reduction loop

Maksym Shpakovych, Geoffrey Maulion, Vincent Kermène, Alexandre Boju, Paul Armand, Agnès Desfarges‐Berthelemot, Alain Barthélémy

2021Optics Express63 citationsDOIOpen Access PDF

Abstract

An innovative scheme is proposed for the dynamic phase control of a laser beam array. It is based on a simple neural network included in a phase correction loop that predicts the complex field array from the intensity of the induced scattered pattern through a phase intensity transformer made of a diffuser. A crucial feature is the use of a kind of reinforcement learning approach for the neural network training which takes account of the iterated corrections. Experiments on a proof-of-concept system demonstrated the high performance and scalability of the scheme with an array of up to 100 laser beams and a phase setting at λ/30.

Topics & Concepts

OpticsLoop (graph theory)Reduction (mathematics)Phase (matter)Beam (structure)Laser beamsArtificial neural networkReinforcementLaserComputer scienceMaterials sciencePhysicsArtificial intelligenceMathematicsComposite materialCombinatoricsGeometryQuantum mechanicsAdaptive optics and wavefront sensingOptical Systems and Laser TechnologyLaser Material Processing Techniques