Robotics and Autonomous Systems

Robots must be able to accomplish tasks in a wide variety of scenarios to be effective in unconstrained environments – they must be able to generalize. For a variety of challenges, we’ve seen excellent outcomes from machine learning algorithms that generalize to large real-world datasets. As a result, machine learning gives robots a potent tool to accomplish the same.

Machine learning algorithms for robotics, on the other hand, frequently generalize narrowly inside a specific laboratory context. In this session, I’ll talk about the problems that robots confront in comparison to traditional machine learning problem settings, and how we might rethink both our robot learning algorithms and our data sources to enable robots to generalize broadly spans jobs, settings, and robot platforms

This course is intended for the following individuals:

Robotics enthusiasts, as well as anyone interested in learning more about robotic, are welcome to attend.