Development of Test-Bed AUV 'ISiMI' and Underwater Experiments on Free Running and Vision Guided Docking

Park, Jin-Yeong; Jun, Bong-Huan; Lee, Pan-Mook; Oh, Jun-Ho

doi:10.5772/6712

Cited by 2 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then the canonical form of feedback linearization function is achieved from AUV nonlinear equations. Nonlinear coefficients of this underwater vehicle are obtained through the dotcom method [42] and verified with experimental results from reference [20].…”

Section: Maneuvering Simulation and Stability Analysismentioning

confidence: 98%

“…Hegrenaes et al [19] presented a simple and intuitive framework for obtaining steady-state maneuvering characteristics of a wide class of AUVs. Developing a test-bed AUV (named ISiMI) and applying some experiments on free running test and vision guided docking is carried out by Park et al [20]. Also, Wang et al [21] modeled a simulator for a mini AUV (named MAUV-II) in spatial motion.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Fig. 3 Verification of simulation with experimental turning test [20] of ISiMI AUV Fig. 4 Rudder command in put-out test and variables including yaw angle w and rate r(t)…”

Section: Put-out Testmentioning

confidence: 99%

See 2 more Smart Citations

Robust control for horizontal plane motions of autonomous underwater vehicles

Kamarlouei

Ghassemi

2015

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

Nowadays autonomous underwater vehicles (AUVs) are employed as unmanned machines in ocean industries. For instance AUVs play an important role in coastal area monitoring and investigating underwater pipe line in deep seas. In this paper, navigation of an AUV near free surface and the effect of wave disturbance and unmodeled hydrodynamics as uncertain terms in control system are addressed. To stabilize the roll motion of the vehicle a practical control mode in mini-UVs is applied. Firstly, a 6-DOF nonlinear dynamic simulator is developed and dynamic stability of the vehicle is investigated. Then, a feedback linearization method is applied to turn the nonlinear system into a convenient linear one, and then a robust technique is applied to guarantee the stability and performance of the system. In addition, a genetic algorithm method is employed for achieving the best gains in feedback linearization control law. Three constraints are considered for optimization including amplitude of sway, yaw and roll motions. Final results show an effective motion control of the AUV in horizontal plane. Meanwhile a reasonable performance of robust control in presence of wave disturbance and un-modeled hydrodynamics is achieved.

show abstract

Section: Maneuvering Simulation and Stability Analysismentioning

confidence: 98%

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Robust control for horizontal plane motions of autonomous underwater vehicles

Kamarlouei

Ghassemi

2015

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…This is the first work which proposes a method for classification and localization of underwater docking stations simultaneously to the best of our knowledge. In [3] and [6], they assume that a docking station remains inside camera's field of view and a fixed threshold is set for binarization so that docking station can be extracted and localized. Similarly, a fixed threshold is set in HSV space in [7].…”

Section: Introductionmentioning

confidence: 99%

Learning Deep Representations and Detection of Docking Stations Using Underwater Imaging

Liu

Özay

Okatani

et al. 2018

2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO)

View full text Add to dashboard Cite

Underwater docking endows AUVs with the ability of recharging and data transfer. Detection of underwater docking stations is a crucial step required to perform a successful docking. We propose a method to detect underwater docking stations using two dimensional images captured under different environmental light variance, deformations aroused by scale and rotation, different light intensity and partial observation. In order to realize our proposed method, we first train Convolutional Neural Networks (CNNs) to learn feature representations and then employ a deep detection network. In order to analyze the performance of the proposed method, we prepared an image dataset of docking stations using underwater imaging. Then, we explore the performance of our method using different data augmentation methods. We improved the AUC of detection by 0.14 using data augmentation and obtained 0.88 AUC with data augmentation. An increment of 0.23 AUC is gained by transfer learning and we obtained 0.88 AUC on another datasets.

show abstract

Development of Test-Bed AUV 'ISiMI' and Underwater Experiments on Free Running and Vision Guided Docking

Cited by 2 publications

References 26 publications

Robust control for horizontal plane motions of autonomous underwater vehicles

Robust control for horizontal plane motions of autonomous underwater vehicles

Learning Deep Representations and Detection of Docking Stations Using Underwater Imaging

Contact Info

Product

Resources

About