论文标题
学习如何行走：暖启动的最佳控制求解器，并记忆运动
Learning How to Walk: Warm-starting Optimal Control Solver with Memory of Motion
论文作者
论文摘要
在本文中，我们提出了一个框架，以建立运动的记忆，以使启动最佳的控制求解器，以实现人形机器人机器人的运动任务。我们使用一种多功能的运动计划者HPP Loco3D来生成一个动态一致的全身轨迹，以存储作为运动的记忆。考虑到所需的接触位置，学习问题被作为回归问题进行了提出的回归问题，以预测单步运动，该接触位置用作产生多步骤运动的构建块。然后，预测的运动被用作快速最佳控制求解器crocoddyl的温暖启动。我们已经表明，该方法设法将所需的迭代数量减少，以从$ \ sim $ 9.5降低到单步运动的$ \ sim $ 3.0迭代，并从$ \ sim $ 6.2到$ \ sim $ \ sim $ 4.5迭代，同时维持溶液的质量。
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.
