Induced differentiation is one of the most experience- and skill-dependent processes in regenerative medicine, and establishing optimal conditions often takes years (an inordinate amount of time). Here, we developed a robotic-AI system that autonomously induces the differentiation of iPS cell-derived RPE (iPSC-RPE) cells. The system performed 216 forty-day cell culture experiments, with a total experimentation time of 8,640 days. The search for optimal differentiation conditions was accelerated using a novel batch Bayesian optimization technique with local penalization, compressing the search time to 185 days, with a cumulative robot operating time of 995 h. From 200 million possible parameter combinations, the system optimized the iPSC-RPE production conditions to yield improved pigmented scores that were up to 88% higher than the scores obtained with the pre-optimized conditions. Transferring tacit knowledge and skills often constitutes a serious obstacle when transposing basic cell experimental research from the laboratory to the medical forefront or for scaling to mass production. Our work demonstrates that autonomous robotic-AI systems can be effectively utilized for the systematic exploration of experimental conditions independently from the tacit knowledge of skilled professionals. This option guarantees immense use in future research.