Continuous Versatile Jumping Using Learned Action Residuals
This work addresses the challenge of robust and agile locomotion for legged robots in difficult terrains, representing a strong specific gain in robotic control.
The authors tackled the problem of enabling quadrupedal robots to perform versatile, continuous jumping motions by proposing a hierarchical framework combining optimal control and reinforcement learning, achieving jumps up to 50cm high, 60cm forward, and 90-degree turns.
Jumping is essential for legged robots to traverse through difficult terrains. In this work, we propose a hierarchical framework that combines optimal control and reinforcement learning to learn continuous jumping motions for quadrupedal robots. The core of our framework is a stance controller, which combines a manually designed acceleration controller with a learned residual policy. As the acceleration controller warm starts policy for efficient training, the trained policy overcomes the limitation of the acceleration controller and improves the jumping stability. In addition, a low-level whole-body controller converts the body pose command from the stance controller to motor commands. After training in simulation, our framework can be deployed directly to the real robot, and perform versatile, continuous jumping motions, including omni-directional jumps at up to 50cm high, 60cm forward, and jump-turning at up to 90 degrees. Please visit our website for more results: https://sites.google.com/view/learning-to-jump.