Knowledge Commons of Institute of Automation,CAS
Adaptive Fusional Localization for Robot Fish Based on Dynamic-weight Fuzzy Inference | |
Yuzhuo Fu1,2; Xiaocun Liao1,2; Ben Lu1,2; Qianqian Zou1,2; Zhuoliang Zhang1,2; Yaming Ou1,2; Chao Zhou1 | |
2022-03-14 | |
会议名称 | 2021 China Automation Congress (CAC) |
会议录名称 | 2021 China Automation Congress (CAC) |
卷号 | 1 |
期号 | 1 |
页码 | 2357-2362 |
会议日期 | 2021-10-22 |
会议地点 | Beijing, China |
会议录编者/会议主办者 | Chinese Association of Automation |
出版地 | Beijing, China |
出版者 | IEEE |
摘要 | Accurate localization of robots in a specific environment often requires the cooperation of multiple sensors, and how to establish a more general data fusion model is always a difficult problem. For the localization of robot fish in an indoor pool environment, this paper proposes an adaptive fusional algorithm based on fuzzy inference of dynamic weights. This paper firstly constructs a confidence probability table of sensors’ signals based on the calibration data sets of BLE and UWB nodes at different distances, as the basis for updating the weights of the BLE or UWB nodes; secondly, the data obtained by each node in a single sampling period in the robot fish movement is vectorized to form a judgment matrix, and then the estimated distance is obtained by fuzzy inference together with the sensor weight; finally, the coordinates are calculated by the four-point positioning method. In this paper, more than 40 sets of experiments have been carried out with a simplified carangidae-like robot fish. The results show that the average positioning error is about 0.189m, which is 88.3% and 31.8% lower than that of using BLE only and using UWB only. In this paper, the fusional positioning method based on statistics combines the advantages of different sensors to reduce the data scale and achieve data denoising while fusing sensor data, which provides a reference for indoor positioning of robot fish and multi-sensor data fusion. |
学科门类 | 工学 ; 工学::控制科学与工程 |
DOI | 10.1109/CAC53003.2021.9727537 |
URL | 查看原文 |
收录类别 | EI |
语种 | 英语 |
EI入藏号 | 721.1 ; 723.2 ; 723.4.1 ; 731.5 |
EI主题词 | Computer Theory, Includes Formal Logic, Automata Theory, Switching Theory, Programming Theory ; Data Processing and Image Processing ; Expert Systems ; Robotics |
EI分类号 | Control Engineering::Automatic Control Principles and Applications |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48563 |
专题 | 复杂系统认知与决策实验室_水下机器人 |
通讯作者 | Chao Zhou |
作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学人工智能学院 |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yuzhuo Fu,Xiaocun Liao,Ben Lu,et al. Adaptive Fusional Localization for Robot Fish Based on Dynamic-weight Fuzzy Inference[C]//Chinese Association of Automation. Beijing, China:IEEE,2022:2357-2362. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Adaptive Fusional Lo(1415KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论