Abstract: Conjugated polymers, with unique (opto) electronic and viscoelastic properties, have undergone remarkable development as promising materials for a wide range of applications such as flexible plastic electronics, large-area printed organic photovoltaics, and energy storage technologies. However, the newly designed materials that promise improved functionalities must first be subjected to a years-long processing effort to meet the performance targets. One of the major hurdles in meeting these performance goals is the high dimensionality of the searching space associated with the formulation and processing variables. To bring quantitative insights to the relative importance and specific influencing behaviors of all variables on the structure and property in a time-efficient fashion, we develop a new experimental paradigm that combines the strengths of multiscale computational methods, rapid and robust experiment acquisition from robotic technologies (i.e., high-throughput processing and characterization) and fast analysis of complex datasets using machine learning (ML). This talk will introduce the utilization of the self-driving lab -PolyBot (https://​www​.anl​.gov/​c​n​m​/​p​o​lybot) for electronic polymer discovery.