Imitation Learning from MPC for Quadrupedal Multi-Gait Control
This work addresses efficient multi-gait control for quadrupedal robots, though it appears incremental as it extends an existing method (MPC-Net) with new loss functions and network specialization.
The paper tackles the problem of training a single policy to control multiple gaits for a walking robot, using an imitation learning approach guided by Model Predictive Control, and demonstrates that the learned policy can replace its teacher on hardware with improved performance over benchmarks like Behavioral Cloning.
We present a learning algorithm for training a single policy that imitates multiple gaits of a walking robot. To achieve this, we use and extend MPC-Net, which is an Imitation Learning approach guided by Model Predictive Control (MPC). The strategy of MPC-Net differs from many other approaches since its objective is to minimize the control Hamiltonian, which derives from the principle of optimality. To represent the policies, we employ a mixture-of-experts network (MEN) and observe that the performance of a policy improves if each expert of a MEN specializes in controlling exactly one mode of a hybrid system, such as a walking robot. We introduce new loss functions for single- and multi-gait policies to achieve this kind of expert selection behavior. Moreover, we benchmark our algorithm against Behavioral Cloning and the original MPC implementation on various rough terrain scenarios. We validate our approach on hardware and show that a single learned policy can replace its teacher to control multiple gaits.