We present a radically robust locomotion controller for quadrupedal robots which is trained using reinforcement learning in simulation. It uses no external sensing like cameras or Lidar and relies only on internal sensors like IMU and joint encoders.
Learn more about this work on our project website:
[ Ссылка ]
Paper links:
- Science Robotics: [ Ссылка ]
- Author's version: [ Ссылка ]
Video by Joonho Lee
