Intuition-enabled machine learning beats the competition when joint human-robot teams perform inorganic chemical experiments

Traditionally, chemists have relied on years of training and accumulated experience in order to discov-er new molecules. But the space of possible molecules so vast, only a limited exploration with the tra-ditional methods can be ever possible. This means that many opportunities for the discovery of inter-esting phenomena have been missed, and in addition, the inherent variability of these phenomena can make them difficult to control and understand. The current state-of-the-art is moving towards the de-velopment of automated and eventually fully autonomous systems coupled with in-line analytics and decision-making algorithms. Yet even these, despite the substantial progress achieved recently, still cannot easily tackle large combinatorial spaces as they are limited by the lack of high-quality data. Herein, we explore the utility of active learning methods for exploring the chemical space by compar-ing collaboration between human experimenters with an algorithm-based search, against their perfor-mance individually to probe the self-assembly and crystallization of the polyoxometalate cluster Na6[Mo120Ce6O366H12(H2O)78]·200H2O (1). We show that the robot-human teams are able to increase the prediction accuracy to 75.6±1.8%, from 71.8±0.3% with the algorithm alone and 66.3±1.8% from only the human experimenters demonstrating that human-robot teams beat robots or humans working alone