Sim-to-Real Learning of Footstep-Constrained Bipedal Locomotion

This is the submission video for the 2022 ICRA (IEEE International Conference on Robotics and Automation) paper “Sim-to-Real Learning of Footstep-Constrained Bipedal Locomotion“ by Helei Duan, Ashish Malik, Jeremy Dao, Aseem Saxena, Kevin Green, Jonah Siekmann, Alan Fern and Jonathan Hurst Preprint link to full paper: Abstract: Recently, work on reinforcement learning (RL) for bipedal robots has successfully learned controllers for a variety of dynamic gaits with robust sim-to-real demonstrations. In order to maintain balance, the learned controllers have full freedom of where to place the feet, resulting in highly robust gaits. In the real world however, the environment will often impose constraints on the feasible footstep locations, typically identified by perception systems. Unfortunately, most demonstrated RL controllers on bipedal robots do not allow for specifying and responding to such constraints. This missing control interface greatly limits the real-world applic