• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Robotics and Automation >Discontinuity-Sensitive Optimal Control Learning by Mixture of Experts
【24h】

Discontinuity-Sensitive Optimal Control Learning by Mixture of Experts

机译：专家混合的不连续性敏感最优控制学习

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

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.
机译：本文提出了一种机器学习方法，以预测给定一些参数输入的相关非线性最佳控制问题的解决方案，例如初始状态。问题参数与最佳解决方案之间的地图称为问题 - 最佳地图，并且由于非凸起，离散同型同型类和控制切换而不连续。这导致传统函数近似器（如神经网络）的困难，这是潜在功能的连续性。本文提出了由分类器和几个回归组组成的专家（MOE）模型的混合，其中每个回归通量被调谐到特定的连续区域。提出了一种新颖的培训方法，可以独立列举分类器和回归。 MOE极大地优于标准的神经网络，在几个动态车辆控制问题中实现了高度可靠的轨迹预测（精度超过99.5％）。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号