Autonomous and data-driven sciences

At the intersection of machine learning and the physical world, we are leveraging automation to accelerate the development of new therapies, materials, and processes. A human working with autonomous or semi-autonomous systems can design and run experiments much more quickly, accurately, and efficiently than a human alone.

Students in our experimental and computational research groups are:

  • combining laboratory automation techniques with powerful large language model (LLMs)
  • doing high-throughput imaging of bacterial interaction and community dynamics
  • developing semi-autonomous workflows to validate closed-loop self-sustaining materials discovery pipelines
  • building on foundational work from our process systems engineering group
  • coupling machine learning with state-of-the-art optimization tools for automated construction of surrogate models
  • investigating machine learning approaches for optimal operation of large complex systems

Work in autonomous sciences is not only increasing throughput but also empowering engineers and scientists to think in new ways to solve intractable problems. Our faculty are thought leaders on the ethical and responsible use of these powerful tools.

Autonomous and data-driven sciences faculty

Gabe Gomes

Gabe Gomes

Assistant Professor
Chemical Engineering, Chemistry

Full profile

John Kitchin

John Kitchin

Professor
Chemical Engineering

Full profile

Tagbo Niepa

Tagbo H.R. Niepa

Arthur Hamerschlag Associate Professor
Chemical Engineering, Biomedical Engineering

Full profile

Anne Skaja Robinson

Anne Skaja Robinson

Trustee Professor
Chemical Engineering

Full profile

Evan Spotte-Smith

Evan Spotte-Smith

Assistant Professor (starting fall 2025)
Chemical Engineering

Full profile

Related news

Carnegie Mellon Cloud Lab

The Carnegie Mellon University Cloud Lab is the world’s first academic cloud lab that allows researchers to remotely control a complete life sciences and chemistry laboratory from their computers.