Abstract In materials science, high-throughput material processing and testing are crucial for rapid materials design and discovery, but manual operations often create bottlenecks in terms of speed and accuracy. Automating the repetitive and labor-intensive aspects of material testing significantly increases throughput and consistency, facilitating a more efficient pathway to material innovation. This study demonstrates automated process control by integrating robotic automation in a high-throughput laser shock system using closed-loop “see-move-shoot” experiments. The system employs two automated linear stages to sequentially manipulate material specimens (flyers) under a laser for impact testing. Each experiment includes automatic target detection, sample centering, laser activation, impact verification, and progression to the next sample. For flyer detection, we developed a computer vision algorithm using a convolutional neural network (CNN) model based on EfficientNetB0. Trained on 16,000 labeled images under various lighting conditions, the model achieved a root mean square error (RMSE) of 0.038 mm in extreme testing conditions (i.e., under high exposure, low light, or blurry images) ensuring reliable and efficient real-time processing. In our “see-move-shoot” comparison study, manual operation took 30.6 seconds for a novice user and 19.2 seconds for an expert user per shot, while the CNN model required only 7.46 seconds. Consequently, the CNN model conducts experiments 4 times faster than the novice user and 2.5 times faster than the expert user.