Video Gallery (selected)

Real-time bipedal robot navigation in dynamic environments.

Control barrier functions and logistic regression for planning around polynomial-shaped obstacles.

Reinforcement learning and cascade policies for robust bipedal locomotion.

Resolved motion control using a linear inverted pendulum model and neural adaptation.

Learned feedback motion policies for Digit walking on rough terrain.

Digit’s first walking gait and small disturbance-rejection tests in the Cyberbotics Lab.

Early exoskeleton walking with the Ohio State controller.

Hybrid zero dynamics informs reinforcement learning for 3D bipedal walking.