Next Steps: Learning a Disentangled Gait Representation for Versatile Quadruped Locomotion
This addresses a limitation in current quadruped locomotion planners for robotics, allowing more versatile and adaptive movement, though it is incremental as it builds on existing gait synthesis methods.
The paper tackled the problem of enabling quadruped robots to continuously vary gait parameters like cadence and footstep height while in motion, achieving a continuous blend of dynamic trot styles with robustness to external perturbations on a real ANYmal robot.
Quadruped locomotion is rapidly maturing to a degree where robots now routinely traverse a variety of unstructured terrains. However, while gaits can be varied typically by selecting from a range of pre-computed styles, current planners are unable to vary key gait parameters continuously while the robot is in motion. The synthesis, on-the-fly, of gaits with unexpected operational characteristics or even the blending of dynamic manoeuvres lies beyond the capabilities of the current state-of-the-art. In this work we address this limitation by learning a latent space capturing the key stance phases of a particular gait, via a generative model trained on a single trot style. This encourages disentanglement such that application of a drive signal to a single dimension of the latent state induces holistic plans synthesising a continuous variety of trot styles. In fact properties of this drive signal map directly to gait parameters such as cadence, footstep height and full stance duration. The use of a generative model facilitates the detection and mitigation of disturbances to provide a versatile and robust planning framework. We evaluate our approach on a real ANYmal quadruped robot and demonstrate that our method achieves a continuous blend of dynamic trot styles whilst being robust and reactive to external perturbations.