Search papers, labs, and topics across Lattice.
5
0
6
3
Humanoid robots can master diverse gaits like walking, running, and stair climbing with a single policy, but only if you selectively apply motion priors to stabilize specific skills.
Bipedal soccer robots can now autonomously recover from falls in under a second thanks to a novel RL framework.
Achieving humanoid robot object manipulation in just 30 minutes could revolutionize deployment efficiency in robotics.
Achieve 100% skill retention in humanoid robots learning new skills by reusing motion priors in a hierarchical tree structure, outperforming multi-task training.
Humanoid robots can now traverse complex terrains with human-like gaits, thanks to a surprisingly simple and efficient framework that eschews adversarial training.
