Learning environmental fields with micro underwater vehicles: a path integral—Gaussian Markov random field approach
Learning environmental fields with micro underwater vehicles: a path integral—Gaussian Markov random field approach
复制标题
DOI：
10.1007/s10514-017-9685-2
复制
发表时间：
2017-12
影响因子：
3.5
通讯作者：
E. Kreuzer;Eugen Solowjow
中科院分区：
文献类型：
--
作者：
E. Kreuzer;Eugen Solowjow
自主水下航行器（auv）在许多科学和商业应用中都取得了进步。当前微电子技术的激增使得小型微型auv （auv）的发展有望在工业应用中获得越来越多的普及，例如监测基于液体的过程。提出了一种基于信息理论的水下航行器储罐探测与监测方法。该控制器基于路径积分控制和高斯马尔可夫随机场（GMRFs）推理的思想。这两部分在PI-GMRF控制器的后退水平方案中组合。该控制问题在随机最优控制域内表述，并将其解表示为路径积分。为了关闭控制理论回路，每个hauv保持用gmrf表示的环境的信念表示，允许通过计算以测量为条件的后验分布进行推理。每个achauv都有自己的控制器实例，并且系统是分散的。仅需要通过通信链路交换每个hauv的测量和预期控制输入。该方法在平流扩散场景的模拟中得到了验证，并对随机游走进行了基准测试，其性能优于随机游走。
Autonomous underwater vehicles (AUVs) are advancing the state of the art in numerous scientific and commercial applications. The current surge in micro electronics enables the development of small micro AUVs (AUVs) which are expected to gain increasing popularity in industrial applications such as monitoring of liquid-based processes. This paper presents an information theoretic approach for exploration and monitoring of liquid containing tanks withAUVs. The controller is based on ideas from path integral control and inference with Gaussian Markov random fields (GMRFs). Both parts are combined in a receding horizon scheme to the PI-GMRF controller. The control problem is formulated within the stochastic optimal control domain and a solution is stated as a path integral. In order to close the control theoretic loop eachAUV maintains a belief representation of the environment expressed with GMRFs which allows reasoning by computing posterior distributions conditioned on measurements. EachAUV has its own controller instance and the system is decentral. Only the exchange of measurements and intended control inputs of eachAUV is required through the communication link. The approach is validated in simulations for an advection–diffusion scenario and benchmarked against random walk, which it outperforms.