Learning How to Walk: Warm-starting Optimal Control Solver with Memory of Motion
This work addresses efficiency in robot motion planning, which is incremental as it builds on existing optimal control methods.
The paper tackles the problem of reducing computation time for optimal control in humanoid robot locomotion by warm-starting the solver with a memory of motion, resulting in a reduction from ~9.5 to ~3.0 iterations for single-step motion and from ~6.2 to ~4.5 iterations for multi-step motion while maintaining solution quality.
In this paper, we propose a framework to build a memory of motion for warm-starting an optimal control solver for the locomotion task of a humanoid robot. We use HPP Loco3D, a versatile locomotion planner, to generate offline a set of dynamically consistent whole-body trajectory to be stored as the memory of motion. The learning problem is formulated as a regression problem to predict a single-step motion given the desired contact locations, which is used as a building block for producing multi-step motions. The predicted motion is then used as a warm-start for the fast optimal control solver Crocoddyl. We have shown that the approach manages to reduce the required number of iterations to reach the convergence from $\sim$9.5 to only $\sim$3.0 iterations for the single-step motion and from $\sim$6.2 to $\sim$4.5 iterations for the multi-step motion, while maintaining the solution's quality.