帮助 关于我们

返回检索结果

一种基于高斯过程回归的AUV自适应采样方法
An AUV Adaptive Sampling Method Based on Gaussian Process Regression

查看参考文献14篇

阎述学 1,2 *   李一平 1   封锡盛 1  
文摘 针对区域海洋特征环境快速观测的需求,提出了一种基于高斯过程回归的小型自主水下机器人(AUV)自适应采样方法.首先,通过比较高斯过程回归(GPR)中使用不同的回归推理方法的估计准确度和计算效率,确定AUV的合适采样间隔时间;在此基础上,根据AUV实时观测的数据进行GPR分析,预测未观测区域环境数据,并通过计算预测区域梯度极值和预测不确定度引导AUV进行在线路径规划;最后使用该方法,对具有不同特征分布的区域环境观测过程进行仿真.结果显示,本方法与常规方法相比,能够更高效地获得观测区域的低误差特征分布估计,更快地获得观测区域热点区特征,更好地适应观测区域特征分布不同的情况.
其他语种文摘 For the rapid observation problem in coastal marine environment,an adaptive sampling method based on Gaussian process regression (GPR) for small autonomous underwater vehicle (AUV) is proposed.Firstly,the estimation accuracies and the computational efficiencies are compared among different regression inference methods in GPR,and the sampling interval time is determined.On this basis,GPR analysis is used to predict the environmental data of unobserved areas based on the real-time observation data from AUV,and the AUV is guided to implement online path planning by calculating the regional gradient extremum and the forecasting uncertainty.Finally,this method is used to simulate the regional environmental observation with different feature distributions.Results show that this method can estimate the low-error feature distribution of the observed area more efficiently than the conventional method,can obtain features of the hot spot area more quickly in the observed area,and is more adaptable to the observed area with different feature distributions.
来源 机器人 ,2019,41(2):232-241 【核心库】
DOI 10.13973/j.cnki.robot.180183
关键词 高斯过程回归 ; 自主水下机器人 ; 自适应采样 ; 在线路径规划 ; 热点区域观测
地址

1. 中国科学院沈阳自动化研究所, 机器人学国家重点实验室, 辽宁, 沈阳, 110016  

2. 中国科学院大学, 北京, 100049

语种 中文
文献类型 研究性论文
ISSN 1002-0446
学科 自动化技术、计算机技术
基金 国家重点研发计划 ;  国家自然科学基金
文献收藏号 CSCD:6463080

参考文献 共 14 共1页

1.  Kemna S. Adaptive informative sampling with autonomous underwater vehicles: Acoustic versus surface communications. OCEANS 2016,2016:8 被引 1    
2.  Zeng J B. Performance of the portable autonomous observation system. OCEANS 2014,2014:4 被引 1    
3.  Das J. Hierarchical probabilistic regression for AUV-based adaptive sampling of marine phenomena. IEEE International Conference on Robotics and Automation,2013:5571-5578 被引 1    
4.  Singh A. Efficient planning of informative paths for multiple robots. 20th International Joint Conference on Artificial Intelligence,2007:2204-2211 被引 1    
5.  Binney J. Optimizing waypoints for monitoring spatiotemporal phenomena. International Journal on Robotics Research,2013,32(8):873-888 被引 1    
6.  Cui R. Mutual information-based multi-AUV path planning for scalar field sampling using multidimensional RRT*. IEEE Transactions on Systems, Man, and Cybernetics-Systems,2017,46(7):993-1004 被引 4    
7.  Hitz G. Adaptive continuousspace informative path planning for online environmental monitoring. Journal of Field Robotics,2017,34(8):1427-1449 被引 2    
8.  Rasmussen C. Gaussian processes for machine learning,2006 被引 11    
9.  Ouyang R. Multi-robot active sensing of non-stationary Gaussian process-based environmental phenomena. International Conference on Autonomous Agents and Multi-agent Systems,2014:573-580 被引 1    
10.  Bai S. Information-theoretic exploration with Bayesian optimization. IEEE/RSJ International Conference on Intelligent Robots and Systems,2016:1816-1822 被引 3    
11.  Ma K C. Data-driven learning and planning for environmental sampling. Journal of Field Robotics,2017 被引 1    
12.  Rasmussen C. Gaussian processes for machine learning (GPML) toolbox. Journal of Machine Learning Research,2010,11(6):3011-3015 被引 1    
13.  Kemna S. Multi-robot coordination through dynamic Voronoi partitioning for informative adaptive sampling in communication-constrained environments. IEEE International Conference on Robotics and Automation,2017:2124-2130 被引 1    
14.  曾俊宝. 便携式自主水下机器人控制系统研究与应用. 机器人,2016,38(1):91-97 被引 8    
引证文献 5

1 程向红 基于改进高斯和粒子滤波的海底地形辅助导航 中国惯性技术学报,2019,27(2):199-204
被引 2

2 乜云利 AUV海洋微结构湍流观测减振方法及实验研究 振动与冲击,2020,39(22):82-88
被引 0 次

显示所有5篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护:中国科学院文献情报中心
地址:北京中关村北四环西路33号 邮政编码:100190 联系电话:(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号