Discontinuity-Sensitive Optimal Control Learning by Mixture of Experts
Discontinuity-Sensitive Optimal Control Learning by Mixture of Experts
复制标题
DOI：
10.1109/icra.2019.8793909
复制
发表时间：
2018-03
期刊：
影响因子：
--
通讯作者：
Gao Tang;Kris K. Hauser
中科院分区：
文献类型：
--
作者：
Gao Tang;Kris K. Hauser
本文提出了一种机器学习方法来预测相关的非线性最优控制问题的解给定一些参数的输入，如初始状态。问题参数到最优解之间的映射称为问题最优映射，由于非凸性、离散同伦类和控制切换，该映射通常是不连续的。这给传统的函数逼近器（如神经网络）带来了困难，因为它假设底层函数是连续的。本文提出了一种混合专家（莫伊）模型，该模型由一个分类器和多个回归器组成，其中每个回归器被调整到一个特定的连续区域。提出了一种独立训练分类器和回归器的新方法。莫伊大大优于标准的神经网络，并实现了高度可靠的轨迹预测（超过99.5%的准确度）在几个动态车辆控制问题。
This paper proposes a machine learning method to predict the solutions of related nonlinear optimal control problems given some parametric input, such as the initial state. The map between problem parameters to optimal solutions is called the problem-optimum map, and is often discontinuous due to nonconvexity, discrete homotopy classes, and control switching. This causes difficulties for traditional function approximators such as neural networks, which assume continuity of the underlying function. This paper proposes a mixture of experts (MoE) model composed of a classifier and several regressors, where each regressor is tuned to a particular continuous region. A novel training approach is proposed that trains classifier and regressors independently. MoE greatly outperforms standard neural networks, and achieves highly reliable trajectory prediction (over 99.5% accuracy) in several dynamic vehicle control problems.