- Some scientific questions are so complex that designing and carrying out the experiments needed to find answers requires a prohibitive amount of scientists’ time.
- Robot scientists could fill the void. One prototype, called Adam, can originate hypotheses about yeast genes and theirfunctions, design experiments to test the ideas and conduct the work.
- Using artificial intelligence, reasoning and robotic hardware, Adam discovered three genes that encode specific yeast enzymes, a determination human scientists had not been able to make.
- Skeptics say Adam is not a scientist, because it requires human input and occasional intervention. But together, human and robot scientists could achieve more than either one alone.
Is it possible to automate scientific discovery? I don’t mean automating experiments. I mean: Is it possible to build a machine—a robot scientist—that can discover new scientific knowledge? My colleagues and I have spent a decade trying to develop one.
We have two main motives. The first is to better understand science. As famed physicist Richard Feynman noted: “What I cannot create, I do not understand.” In this philosophy, trying to build a robot scientist forces us to make concrete engineering decisions involving the relation between abstract and physical objects and between observed and theoretical phenomena, as well as the ways hypotheses are created.
This article was originally published with the title Rise of the Robo Scientists.