<ul><li>Pyramid wavefront sensors (PWFSs) are the preferred choice for extreme adaptive optics (XAO) systems.</li><li>The first on-sky demonstration of XAO with an unmodulated PWFS using a nonlinear reconstructor based on convolutional neural networks is presented.</li><li>The real-time implementation on the Magellan Adaptive Optics eXtreme (MagAO-X) instrument demonstrates successful closed-loop operation at high frequencies (>2 kHz).</li><li>The unmodulated PWFS shows comparable performance to the modulated PWFS under favorable conditions and potential for improvement on fainter stars.</li></ul>

Making the unmodulated pyramid wavefront sensor smart II. First on-sky demonstration of extreme adaptive optics with deep learning

Discover more