A Vision System for an Autonomous Underwater Vehicle

The visual information is very important for the operation of an underwater vehicle such as a manned vehicle and a remotely operated vehicle (ROV). And it will be also essential for functions which should be applied to an autonomous underwater vehicle (AUV) for the next generation. Generally, it is got by optical sensors, and most underwater vehicles are equipped with various types of them. Above all, camera systems are applied as multiple units to the underwater vehicles. And they can construct a stereo camera system. In this paper, some new functions, which provide some type of visual information derived by the stereo vision system, are described. And methods to apply the visual information to the underwater vehicle and their utility are confirmed.

Download Full-text

Vision System for an Autonomous Underwater Vehicle with a Benthos Sampling Function

Journal of Robotics and Mechatronics ◽

10.20965/jrm.2018.p0248 ◽

2018 ◽

Vol 30 (2) ◽

pp. 248-256 ◽

Cited By ~ 2

Author(s):

Shinsuke Yasukawa ◽

Jonghyun Ahn ◽

Yuya Nishida ◽

Takashi Sonoda ◽

Kazuo Ishii ◽

...

Keyword(s):

High Speed ◽

Autonomous Underwater Vehicle ◽

Vision System ◽

Image Acquisition ◽

Underwater Vehicle ◽

Sampling Function ◽

Software Modules ◽

Preparation Mode ◽

Time Required ◽

Mode Tm

We developed a vision system for an autonomous underwater robot with a benthos sampling function, specifically sampling-autonomous underwater vehicle (AUV). The sampling-AUV includes the following five modes: preparation mode (PM), observation mode (OM), return mode (RM), tracking mode (TM), and sampling mode (SM). To accomplish the mission objective, the proposed vision system comprises software modules for image acquisition, image enhancement, object detection, image selection, and object tracking. The camera in the proposed system acquires images in intervals of five seconds during OM and RM, and in intervals of one second during TM. The system completes all processing stages in the time required for image acquisition by employing high-speed algorithms. We verified the effective operation of the proposed system in a pool.

Download Full-text

Modeling and Development of an Autonomous Underwater Vehicle ARYA for Object Recognition

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.b2843.078219 ◽

2019 ◽

Vol 8 (2) ◽

pp. 5505-5510

Keyword(s):

Undergraduate Students ◽

Structural Design ◽

Power Distribution ◽

Autonomous Underwater Vehicle ◽

Vision System ◽

Dynamic Control ◽

Underwater Vehicle ◽

Control Algorithms ◽

Technological University ◽

Made In

Arya is an autonomous underwater vehicle (AUV) modeled and developed by team DTU-AUV comprising of undergraduate students from multidisciplinary backgrounds of Delhi Technological University (DTU), India, to participate in an IEEE backed Singapore AUV Challenge (SAUVC). This paper entails the rationale and methodology employed to design and integrate various systems onboard. Significant improvisations have been made in the structural design of the vehicle to enhance its hydrodynamic stability and maneuverability to perform discrete tasks in comparison to the previous vehicles developed by the team. The focus is laid on the embedded and power system to enhance reliability, modularity, and power distribution. The software stack is designed to run in decentralized multi-threaded agent architecture, with the threads handling pressure sensor, cameras, control system, IMU, mission planner each performing input and output operations in continuous loops. PID control algorithms achieve the desired dynamic control. The vision system is devised to monitor the marine environment and detect underwater contoured objects.

Download Full-text