A Novel Underwater Simultaneous Localization and Mapping Online Algorithm Based on Neural Network

Hou, Guangchao; Shao, Qi; Zou, Bo; Dai, Liwen; Zhang, Zhe; Mu, Zhehan; Zhang, Yadong; Zhai, Jingsheng

doi:10.3390/ijgi9010005

Cited by 11 publications

(3 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The criterion for selecting an appropriate sensor depends on speed or range of the scan. Then mainly LiDAR (Light Detecting And Ranging), sonar or magnetic SLAM sensors are used [8]. Nowadays, SLAM based navigation systems dominate in fully autonomous vehicle navigation systems.…”

Section: Acoustic Localizationmentioning

confidence: 99%

Directions of Development of the Autonomous Unmanned Underwater Vehicles. A Review

Orłowski

2022

Maritime Technical Journal

View full text Add to dashboard Cite

In the paper review of unmanned underwater vehicle (AUV) is presented. The description of main systems is depicted with focus on autonomous single vehicle as well as a swarm. As a consequence of development of AUV technology, research centers are focused on issues related to increasing the degree of their autonomy. Nowadays, mostly navigation and communication as well as high-efficient propeller systems are being developed. There are problems linking this issues. Their solutions includes development of new control laws containing algorithms to prevent collisions - for unmanned vehicles with elements of the underwater environment and for several underwater vehicles cooperating with each other in a swarm.

show abstract

Section: Acoustic Localizationmentioning

confidence: 99%

Directions of Development of the Autonomous Unmanned Underwater Vehicles. A Review

Orłowski

2022

Maritime Technical Journal

View full text Add to dashboard Cite

show abstract

“…The Levenberg–Marquardt algorithm is used. Hou et al perform an interesting machine learning approach [ 18 ]. They present an Auto Mobile Base Simultaneous localization and mapping (AMB-SLAM) online navigation algorithm based on an artificial neural network (ANN) and measurements from randomly distributed beacons of low-frequency magnetic fields.…”

Section: Introductionmentioning

confidence: 99%

In Situ Underwater Localization of Magnetic Sensors Using Natural Computing Algorithms

Alimi¹,

Fisher

Nahir³

2023

Sensors

View full text Add to dashboard Cite

In the shallow water regime, several positioning methods for locating underwater magnetometers have been investigated. These studies are based on either computer simulations or downscaled laboratory experiments. The magnetic fields created at the sensors’ locations define an inverse problem in which the sensors’ precise coordinates are the unknown variables. This work addresses the issue through (1) a full-scale experimental setup that provides a thorough scientific perspective as well as real-world system validation and (2) a passive ferromagnetic source with (3) an unknown magnetic vector. The latter increases the numeric solution’s complexity. Eight magnetometers are arranged according to a 2.5 × 2.5 m grid. Six meters above, a ferromagnetic object moves according to a well-defined path and velocity. The magnetic field recorded by the network is then analyzed by two natural computing algorithms: the genetic algorithm (GA) and particle swarm optimizer (PSO). Single- and multi-objective versions are run and compared. All the methods performed very well and were able to determine the location of the sensors within a relative error of 1 to 3%. The absolute error lies between 20 and 35 cm for the close and far sensors, respectively. The multi-objective versions performed better.

show abstract

“…In order to reduce errors, digital filtering is an essential part for positioning algorithm. e commonly used filtering algorithms mainly include the least square method [6], Kalman filter [7,8], GDOP weighting [9,10], error classification [11], coordinate transformation [12], neural network [13,14], and other intelligent algorithms such as a genetic algorithm [15,16]. Among them, the Kalman filter makes noise suppression more effective, and positioning accuracy further improved because it does not impose too strict limits on error forms and its unique data fusion function.…”

Section: Introductionmentioning

confidence: 99%

A Dynamic-Weighted Attenuation Memory Extended Kalman Filter Algorithm and Its Application in the Underwater Positioning

Guo

Wang

2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Extended Kalman filter (EKF) plays an important role in the acoustic signal processing of underwater positioning. However, accumulative errors and model inaccuracies lead to divergence. Then, attenuation memory EKF is created in response to this issue which needs to manually select all or part of the parameters. Thus, a dynamic-weighted attenuation memory EKF is proposed. Firstly, several underwater positioning simulations under different conditions are carried out. Results show, with the change of parameter conditions in positioning, the ideal attenuation coefficient changes between 0.5 and 1, but it is difficult to express it in function formula or statistical form. Secondly, a dynamic selection method of attenuation factor is designed. In the later contrast simulation, the proposed method has improved the positioning performance compared with the existing attenuation memory filter algorithm. Finally, the results of physical model verification experiment show that the dynamic-weighted attenuation memory EKF algorithm not only suppresses divergence better but also avoids the subjectivity of attenuation coefficient selection to a certain extent.

show abstract

A Novel Underwater Simultaneous Localization and Mapping Online Algorithm Based on Neural Network

Cited by 11 publications

References 78 publications

Directions of Development of the Autonomous Unmanned Underwater Vehicles. A Review

Directions of Development of the Autonomous Unmanned Underwater Vehicles. A Review

In Situ Underwater Localization of Magnetic Sensors Using Natural Computing Algorithms

A Dynamic-Weighted Attenuation Memory Extended Kalman Filter Algorithm and Its Application in the Underwater Positioning

Contact Info

Product

Resources

About