The Structured Techniques for Algorithmic Robotics (STAR) Lab at Georgia Tech, directed by Harish Ravichandar, builds structured computational and learning frameworks that combine classical tools with latest advances in machine learning to improve robots’ efficiency, reliability, and generalizability. To this end, we identify, study, and inject approproate inductive biases into our algorithms in the form of architectures, objective functions, and constraints. Our research is motivated by and pertinent to diverse robotics applications, ranging from dexterous manipulation to multi-agent coordination. We are affliated with the Institute for Intelligent Robots and Machines (IRIM).

Want to get involved?: We are looking to recruit both graduate and undergraduate students to work on exciting projects in dexterous manipulation, and multi-agent coordination. If you are interested, we request that you take the time to read some of our recent papers to get a better sense of our research interests before contacting us. When you reach out, please share the specific research questions that excite you and why you want to investigate them at our lab in particular.

A short (~15 mins) talk that provides a very high-level overview of our research. You can also find it here.