Automation of nanoindentation targeting control using machine vision.

Nanoindentation is vital for probing mechanical properties at the nano- to micron-scale. However, traditional grid-based workflows are inefficient for targeting specific microstructural features. An automated nanoindentation framework is presented, designed to support machine-learning-enabled experimentation. The system operates in three modes: standard automation, feature-based indentation via image-to-coordinate mapping, and large-scale indentation with full alignment along the x, y, and z axes. Precise indentation is achieved by directly aligning the sample beneath the indenter, thereby mitigating initial travel-distance errors (2.5-6 μm). Pixel-to-micron calibration enables accurate navigation between optical images and physical indentation locations. Benchmark demonstrations illustrate phase-specific and orientation-guided indentation enabled by Self-Organizing Feature Maps and macro imaging. The framework enhances precision, reduces user intervention, and enables efficient targeted characterization of complex materials. By establishing a direct interface between nanoindentation systems and Python-based automation frameworks, the approach can be adapted across most existing nanoindenter platforms. This work lays the foundation for next-generation autonomous mechanical testing of microstructurally complex materials.