Self-driving labs use artificial intelligence (AI) and computational modelling to predict which advanced materials or small molecules will have the properties (e.g. conductivity) required for a particular application. A robotic lab then uses these predictions to autonomously synthesize and tests for said properties. This data is then fed back into the AI system, so that it can learn from the results to generate a new, better slate of candidates. After rounds of predictions, syntheses, and tests, a winner emerges. By inverting the usual discovery process, this closed-loop technology allows scientists to first define the desired properties and then work backwards to develop whole families of new materials without tedious hours of trial and experiments in the lab.
For example, advanced materials represent up to 50% of the manufacturing cost of clean energy technology, and this is expected to increase to 80% in the near future. Realizing these technological solutions requires the discovery of novel advanced materials that are more efficient, longer lasting, less expensive, and more environmentally-friendly. As a foundational technology, self-driving labs can be applied to a wide range of areas that are critical to our socio-economic well-being and the planet.
Clear parallels exist between the high cost and long timelines of materials development to genome sequencing prior to the advent of the Human Genome Project. New sequencing technologies led to the exponential decrease in the cost and time required to decode the genomes of living organisms. These developments revolutionized biology, created the discipline of genomics, and led to the explosion of the biotech industry.