Rapid Locomotion via Reinforcement Learning
This addresses the problem of enabling fast and stable movement for legged robots in real-world environments, though it builds incrementally on prior sim-to-real transfer methods.
The paper tackled agile locomotion for legged robots in natural terrains, achieving a record speed of 3.9 m/s for the MIT Mini Cheetah with robust performance on grass, ice, and gravel.
Agile maneuvers such as sprinting and high-speed turning in the wild are challenging for legged robots. We present an end-to-end learned controller that achieves record agility for the MIT Mini Cheetah, sustaining speeds up to 3.9 m/s. This system runs and turns fast on natural terrains like grass, ice, and gravel and responds robustly to disturbances. Our controller is a neural network trained in simulation via reinforcement learning and transferred to the real world. The two key components are (i) an adaptive curriculum on velocity commands and (ii) an online system identification strategy for sim-to-real transfer leveraged from prior work. Videos of the robot's behaviors are available at: https://agility.csail.mit.edu/