Machine learning post processing of underwater vehicle pressure sensor array for speed measurement

Ramirez, Wilmer Ariza; Leong, ZQ; Nguyen, Hung D.; Jayasinghe, Shantha Gamini

doi:10.1016/j.oceaneng.2020.107771

Cited by 4 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, if only the INS is used for navigation, there are inevitable integration errors, which are usually corrected by additional velocity measurement systems. Compared with existing navigation systems and underwater velocity measurement systems, such as the Doppler velocity log (DVL) system, [51] computer vision systems, [52] and pressure sensing systems, [2,53] our tactile sensor can measure velocity wirelessly, keeping the hull or bulkhead intact, with a small volume, light weight, flexibility, and low cost, which demonstrates the potential on the velocity measurement of the underwater vehicles, especially deep-sea small AUVs.…”

Section: Navigation Application Of Fluid Velocity Measurementmentioning

confidence: 99%

Split‐Type Magnetic Soft Tactile Sensor with 3D Force Decoupling

Dai,

Zhang,

Pan

et al. 2023

Advanced Materials

View full text Add to dashboard Cite

Tactile sensory organs for sensing 3D force, such as human skin and fish lateral lines, are indispensable for organisms. With their sensory properties enhanced by layered structures, typical sensory organs can achieve excellent perception as well as protection under frequent mechanical contact. Here, inspired by these layered structures, a split‐type magnetic soft tactile sensor with wireless 3D force sensing and a high accuracy (1.33%) fabricated by developing a centripetal magnetization arrangement and theoretical decoupling model is introduced. The 3D force decoupling capability enables it to achieve a perception close to that of human skin in multiple dimensions without complex calibration. Benefiting from the 3D force decoupling capability and split design with a long effective distance (>20 mm), several sensors are assembled in air and water to achieve delicate robotic operation and water flow‐based navigation with an offset <1.03%, illustrating the extensive potential of magnetic tactile sensors in flexible electronics, human‒machine interactions, and bionic robots.

show abstract

Section: Navigation Application Of Fluid Velocity Measurementmentioning

confidence: 99%

Split‐Type Magnetic Soft Tactile Sensor with 3D Force Decoupling

Dai,

Zhang,

Pan

et al. 2023

Advanced Materials

View full text Add to dashboard Cite

show abstract

“…For example, Rauchenstein et al [12] applied ML classification and regression algorithms to calibrate the localization errors of an acoustic sensor array based on the time-difference-of-arrival (TDOA), markedly decreasing the median distance error for both the stationary tracks and the mobile tracks. Ramirez et al [13] employed the ML technique to account for the nonlinearity caused by the vehicle acceleration at the estimated speed, improving the post-processing accuracy. Considering these capabilities of ML in data processing and nonlinear fitting, ML is introduced into the post-processing of the magnetic data for the localization of the underwater projectile.…”

Section: Introductionmentioning

confidence: 99%

Research on TMR-FCN-based underwater projectile localization method

Huang

Liu³

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

A machine learning localization method for underwater projectile using Tunnel magnetoresistance (TMR) sensors is proposed in this paper. Firstly, the relation between the magnetic field intensity and the position of the projectile was built based on the magnetic dipole model. Then, the measurement model of TMR sensors was constructed to offer the voltage signal linearly correlated to the magnetic field intensity, and the network model based on the fully connected neural network (FCN) was established to approximate and regress the highly nonlinear mapping function between the magnetic field intensity (B) and the square of the distance from the projectile to the sensor (d2). Inspired by the Received Signal Strength (RSS) localization method, the least-square method was adopted to solve the actual coordinate of the projectile. Finally, to verify the localization accuracy of the proposed TMR-FCN-based method, the ballistic simulation was performed for providing the actual position of the projectile and the output of the TMR sensors, then the positioning operation was carried out by coupling the FCN model and the least-square method. The results demonstrate that the B-d2 model can fast compute the d2 within 8ms for the single given B and the overall mean accuracy is up to 99.15%. The localization distance error via the least-square method is lower than 0.5mm. These results indicate that the TMR-FCN-based localization method can achieve accurate localization for the underwater projectile and effectively overcome the tough problem of solving the high-dimensional nonlinear equations for B and d2.

show abstract