Real-Time Whole-Body MPC for Legged Robots with MuJoCo
We show that simple model-predictive controls algorithms such as iLQR can be surprisingly effective at enabling a variety of whole-body control behaviors on high dimensional legged robtots (i.e. quadrupeds and humanoids) in the real world.
Checkout our website.
Related Papers
|
2025 March |
Whole-Body Model-Predictive Control of Legged Robots with MuJoCo
arxiv (In Review) |
People
John Zhang
GPU Accelerated Optmization and Control through Contact
Taylor Howell
Google DeepMind
Zac Manchester
Associate Professor