Inspección visual subacuática mediante robótica submarina
Marc Carreras, Pere Ridao, Rafael García, David Ribas, Narcís Palomeras
- 发表年份
- 2012
- 引用次数
- 5
- 访问权限
- 开放获取
摘要
This article presents an industrial application of underwater robotics for visual inspection of the seabed. The system consists of an underwater robot to acquire visual images at a very short distance (1-2 meters) from the surface to be inspected and an underwater localization system installed in a boat or in a mooring buoy. This system estimates the robot absolute position during the inspection in Earth coordinates using a USBL acoustic locator, an inertial navigation system (INS) and a GPS. Moreover, the robot has its own navigation system onboard, based on EKF, which uses a velocity sensor based on Doppler effect and an INS with a fiber optic gyroscope (FOG). The control architecture of the robot allows the inspection to be in teleoperation, semi-autonomous or autonomous mode. The robot can perform the inspection in 2D vertical or horizontal surfaces. Once the images and all navigation data have been acquired, an offline process is executed for data fusion, and the processing of the images ends up with a 2D georeferenced image mosaic from the inspected area. The paper details the developed technologies and describes a campaign in the Mequinenza reservoir to detect zebra mussel populations.
关键词
相关论文
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002