After one day of implementation and training with the armatures from BeyondMimic, we reproduced this very dynamic motion using G1! Wonderful system id!
109,673 次观看
Using attention-based map encoding, we enable robots to traverse extremely sparse terrains. We are now developing a new architecture that explicitly plans contact points, rather than latent representations, enabling whole-body contact planning for humanoid robots. Stay tuned.
23,549 次观看
Tracking is too limited. Now we do navigation-based parkour!
