Legged robots offer the potential to navigate a much
wider range of terrain than their wheeled counterparts,
allowing for robotic applications in places where they
are currently not possible. However, legged robots
currently lag far behind their biological cousins in
terms of their ability to navigate challenging terrain.
In this talk we discuss the application of machine
learning techniques to achieve state-of-the-art
performance for quadruped locomotion over rough terrain.
Zico Kolter is PhD student in Computer Science at
Stanford University, working with Professor Andrew Ng.
His research focuses on machine learning, control, and
robotics, with a focus on quadruped robots in
particular.
