Near-optimal task-driven sensor network configuration
Near-optimal task-driven sensor network configuration
复制标题
近乎最优的任务驱动传感器网络配置
DOI：
10.1016/j.automatica.2023.110966
复制
发表时间：
2023
期刊：
影响因子：
6.4
通讯作者：
Cowlagi, Raghvendra V.
中科院分区：
文献类型：
--
作者：
St. Laurent, Chase;Cowlagi, Raghvendra V.
提出了一种耦合路径规划和传感器配置的方法。路径规划的目标是最大限度地减少暴露在未知的空间变化的标量场中，称为威胁场，由传感器网络测量。利用高斯过程回归方法从这些测量值中估计出威胁区域。重要的是，传感器是可配置的，即可以改变位置和视场大小等参数。这项工作的一个主要创新是通过最大化所谓的任务驱动信息增益(TDIG)度量来执行传感器配置，该度量量化了规划路径成本的不确定性降低。为了提高计算效率，引入了一种称为自适应互信息(SAMI)的替代度量，并证明该度量是子模的。结果表明，该方法在寻找近似最优方案所需的测量次数方面，大大优于传统的解耦信息驱动传感器配置。
A coupled path-planning and sensor configuration method is proposed. The path-planning objective is to minimize exposure to an unknown spatially-varying scalar field, called the threat field, measured by a network of sensors. Gaussian Process regression is used to estimate the threat field from these measurements. Crucially, the sensors are configurable, i.e., parameters such as location and size of field of view can be changed. A main innovation of this work is that sensor configuration is performed by maximizing a so-called task-driven information gain (TDIG) metric, which quantifies uncertainty reduction in the cost of the planned path. For computational efficiency, a surrogate metric called the self-adaptive mutual information (SAMI) is introduced and shown to be submodular. The proposed method is shown to vastly outperform traditionally decoupled information-driven sensor configuration in terms of the number of measurements required to find near-optimal plans.
多智能体数据融合的动态路径规划 - 并行分层重新规划器
DOI：
10.1109/robot.2009.5152883
发表时间：
2009
期刊：
2009 IEEE International Conference on Robotics and Automation
影响因子：
--
作者：
Thomas Allen;A. Hill;J. Underwood;S. Scheding
通讯作者：
S. Scheding