arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.02863cs.ROcs.LG
收藏

规划在无限时域模型预测控制中的价值

The Value of Planning for Infinite-Horizon Model Predictive Control

University of Washington(华盛顿大学)

Nathan Hatch, Byron Boots

摘要:

模型预测控制(MPC)是一种经典的工具,用于对复杂的现实世界系统进行最优控制。虽然它已经成功地应用于机器人技术中的各种具有挑战性的任务,但它从根本上受到预测范围的限制,如果太短,将导致短视的决策。最近,一些论文建议使用学习的价值函数作为MPC的终端成本。如果价值函数是准确的,它有效地允许MPC在无限范围内进行推理。不幸的是,强化学习(RL)解决方案的价值函数近似可能难以实现机器人任务。在本文中,我们提出了一个更有效的方法,适用于目标导向的问题,如达到和导航的价值函数近似。在这些问题中,MPC通常被制定为跟踪规划器返回的路径或轨迹。然而,这种策略是脆弱的,因为对机器人的意外扰动将需要重新规划,这在运行时可能是昂贵的。相反,我们展示了现代规划者使用的中间数据结构如何被解释为近似的价值函数。我们表明,这个价值函数可以直接使用MPC,从而在运行时更有效和弹性的行为。

英文摘要:

Model Predictive Control (MPC) is a classic tool for optimal control of complex, real-world systems. Although it has been successfully applied to a wide range of challenging tasks in robotics, it is fundamentally limited by the prediction horizon, which, if too short, will result in myopic decisions. Recently, several papers have suggested using a learned value function as the terminal cost for MPC. If the value function is accurate, it effectively allows MPC to reason over an infinite horizon. Unfortunately, Reinforcement Learning (RL) solutions to value function approximation can be difficult to realize for robotics tasks. In this paper, we suggest a more efficient method for value function approximation that applies to goal-directed problems, like reaching and navigation. In these problems, MPC is often formulated to track a path or trajectory returned by a planner. However, this strategy is brittle in that unexpected perturbations to the robot will require replanning, which can be costly at runtime. Instead, we show how the intermediate data structures used by modern planners can be interpreted as an approximate value function. We show that that this value function can be used by MPC directly, resulting in more efficient and resilient behavior at runtime.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑