Our goal is to develop experimental and computational tools that can be used in conjunction with data-driven machine learning methods to design, model, and build smart programmable structures. We are also interested in understanding the mechanics of a variety of engineering and natural systems, e.g. deployable structures in engineering and bacterial locomotion in nature.
We take a highly interdisciplinary approach combining computation, robotics, and machine learning towards the ultimate goal of uncovering the mechanics of solids and structures. We are inspired by the emerging fields of artificial intelligence, computer graphics, and collaborative robotics, and seek to employ these tools in our research.
Putting it simply: we need to generate a lot of data to enable data-driven learning. Our approach is twofold:
- Numerical: fast and efficient numerical simulation tools that serve as the source of data for machine learning algorithms
- Experimental: collaborative robots that semi-autonomously perform experiments to gather data