Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture discusses the development of medium-sized robots capable of agile locomotion in human-scale environments. The instructor explains the use of Center Pathet Generators (CPGs) to control the robot's movements, comparing them to model-based approaches and machine learning. The lecture covers trajectory optimization methods, different robot models, and the challenges faced in tuning the CPGs. The instructor also explores the importance of exploiting the full dynamics of the robot and the potential benefits of using CPG networks for agile maneuvers. The lecture concludes with a discussion on optimizing the robot's performance, overcoming local minima, and the future research objectives to achieve extreme agile locomotion.