Learning Emergent Gaits with Decentralized Phase Oscillators: on the role of Observations, Rewards, and Feedback
This work addresses locomotion control for quadrupedal robots by enabling emergent gaits through decentralized feedback, though it is incremental in its approach.
The authors tackled the problem of learning quadrupedal locomotion by developing a minimal phase oscillator model that uses local feedback of ground reaction forces, resulting in emergent gait preferences without prescribing specific gaits.
We present a minimal phase oscillator model for learning quadrupedal locomotion. Each of the four oscillators is coupled only to itself and its corresponding leg through local feedback of the ground reaction force, which can be interpreted as an observer feedback gain. We interpret the oscillator itself as a latent contact state-estimator. Through a systematic ablation study, we show that the combination of phase observations, simple phase-based rewards, and the local feedback dynamics induces policies that exhibit emergent gait preferences, while using a reduced set of simple rewards, and without prescribing a specific gait. The code is open-source, and a video synopsis available at https://youtu.be/1NKQ0rSV3jU.