Shiekh Zia Uddin, Sachin Vaidya, Shrish Choudhary, Zhuo Chen, Raafat K Salib, Luke Huang, Dirk R Englund, Marin Soljačić
Optical experiments are essential across science and technology, yet their design, assembly, and alignment remain predominantly manual, limiting throughput, reproducibility, and scalability. Automating such experiments is challenging because of stringent precision requirements and the diversity of setups in typical real-world optical laboratory environments. Here, we introduce a platform that integrates generative artificial intelligence, computer vision, and precision robotics to automate free-space optical experiments. The system translates user-defined goals into valid optical configurations, assembles them with submillimeter accuracy, and performs micrometer-scale fine alignment using a robotic tool. It then executes a range of accurate measurements, including beam characterization, polarization mapping, and spectroscopy. This work establishes a platform for reconfigurable optics automation, potentially enabling programmable and adaptive experimental workflows.