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 presents the paper 'Nonlinear Stochastic Trajectory Optimization for Centroidal Momentum Motion Generation of Legged Robots' by A. Gazar, M. Khadiv, S. Kleff, A. Del Prete, and L. Righetti. It covers topics such as planning robust multi-contact trajectories for legged robots, centroidal momentum dynamics, friction pyramid constraints, uncertainty-aware friction pyramid constraints, and whole-body planning framework. The lecture also discusses trotting motion on unplanned debris, reduced floor friction, force distribution, and the comparison between nominal and stochastic trajectory optimization.