Goto

Collaborating Authors

Robot bridge inspector uses sensors and machine learning to hunt for defects

@machinelearnbot

Robot bridge inspector uses sensors and machine learning to hunt for defects Researchers at the University of Nevada have developed an autonomous robot, designed to inspect bridges and detect any structural damage before it can cause potential injury. The four-wheeled robot bridge inspector, called Seekur, uses a variety of tools to carry out its important task. Researchers at the University of Nevada have developed an autonomous robot, designed to inspect bridges and detect any structural damage before it can cause potential injury. The four-wheeled robot bridge inspector, called Seekur, uses a variety of tools to carry out its important task.


Thirty Meter Telescope Project Is Stalled, but the Robot Needed to Build It Is Ready

IEEE Spectrum Robotics

The prosaically named Thirty Meter Telescope (TMT) project, a planned observatory to be built on Mauna Kea, the Big Island, in Hawaii, is huge in every way: a reported US 1.4 billion dollar budget, a giant mirror composed of 492 smaller mirror segments, and a goal of investigating not just the stars in our Milky Way but galaxies forming at the very edge of the observable universe. Though this project is backed by the governments of China, Japan, Canada, and India, as well as the United States, it may never be built. For its location is considered sacred by some Hawaiians, whose protests have been heard all the way to the State Supreme Court of Hawaii, which in December 2015 invalidated TMT's previously granted building permit. With the project suspended for over a year, involved scientist and construction companies can only keep their fingers crossed that the contested case will go their way. In the meantime, Mitsubishi Electric, which has developed the main structure of TMT, announced this week the completion of a prototype robot for a segmented-handling system (SHS) to install and replace the mirror segments.


Yes, the Robots Are Coming for Our Jobs, But Just the Boring Ones

#artificialintelligence

Which of America's bridges are getting ready to collapse? More than 600,000 bridges in the U.S. are due for inspection. Traditionally, divers are sent out to visually examine the bridges' underwater structures. The work is time-consuming, expensive, and tedious, and can be dangerous. Karl von Ellenrieder and his team at Florida Atlantic University's Dania Beach campus are working on a fleet of intelligent, autonomous boats that could replace many of those divers.


Robot inspector helps check bridges for dangerous defects

New Scientist

When the I-35W bridge over the Mississippi river in Minnesota collapsed in 2007, killing 13 people, it was because of defects in steel plates that safety inspectors had missed. A new robot helper could help avoid such tragedies by making bridge checks cheaper and more accurate. Surveying a bridge used to involve drilling into the road to check the concrete and steel structures underneath. Although radar has simplified the work since the 1980s, sending out teams of people to check bridges is still expensive and can require extended road closures. The upshot is that many bridges are overdue a health check – thousands in the US alone, for instance.


Robot bridge inspector uses sensors and machine learning to hunt for defects

#artificialintelligence

Autonomous bridge-inspecting robot could save lives by using smart sensors and machine learning algorithms to detect dangerous defects. Researchers at the University of Nevada have developed an autonomous robot, designed to inspect bridges and detect any structural damage before it can cause potential injury. The four-wheeled robot bridge inspector, called Seekur, uses a variety of tools to carry out its important task. These include ground-penetrating radar for looking beneath the surface of a bridge for underlying instabilities, sensors designed to search for possible corrosion of steel or cement, and a camera which analyzes cracks in the bridge's surface. A machine learning algorithm then analyzes all of this information and uses it to generate a color-coded map, which is passed on to (human) engineers to make them aware of weak spots.