Robots Horizon She says she has successfully automated window washing for the world’s skyscrapers – a task that has been done by hand for more than 100 years.
To automate the task of cleaning windows, Skyline has developed “Ozmo”, a system that combines an industrial robot, a computerized vision system, artificial intelligence (AI) and machine learning technologies.
What previously required three to four months of manual labor, Ozmo does automatically in about half the time. But most importantly, the system ensures safety by removing the human workers from the window washing platform or “basket”.
Manual window cleaning requires three or four people – two people in the basket, one on the roof and, in some cases, another person on the floor. Ozmo requires only one person on the roof to control the basket, power and water sources and the crane, while the robot cleans.
For power and water supply, Ozmo is defined to fit the existing building maintenance unit (BMU) infrastructure. Inside the basket is a table that houses several types of sensors and computers.
The robotic arm and its Lidar (light detection and ranging) camera, which uses lasers for imaging, are placed on top of a table. Once the table is installed in the pre-existing window washing basket in the building, the system is ready to go.
According to Ross Bloom, COO of Skyline Robotics, the Skyline team has been working on Project Ozmo for the past five years and takes frequent steps along the way to integrate all the necessary technical pieces.
This includes the industrial robot itself and the programming that enables its arm to simulate the movements of a human to clean windows.
“The robot arm connects to a Lidar camera that provides a ‘vision’ of the robot and a torque sensor at the end of the cleaning brush that gives the Ozmo a ‘touch’ feel,” Blum says.
“The system software acts as a brain and collects data from several different cameras and sensors at a rate of about 200 times/sec to adjust the robot’s movements and achieve the most efficient cleaning path while automating Ozmo’s descent down the side of a skyscraper.”
For the Ozmo system, Skyline uses the waterproof version of a Coca Robotics KR Agilus industrial robot combined with software-based artificial intelligence makes window washing application possible.
Skyline has developed an algorithm that allows feedback to control the force and other variables that then control the amount of pressure the robot applies to the glass.
The reach of the robot extends to 1.1 metres. According to Blum, “One of the biggest factors in choosing Skyline KUKA was not only the brand’s credibility and the global team behind it, but also because KUKA’s robotic arm can handle the rigors of the outdoor environment, while the majority of other brands fail to do so.”
He went on to say that the robots are IP65 rated and very reliable, and that their six-axis movement was also important to Skyline, especially when it came to approaching the complex facade geometries it encounters in the building.
The Kuka KR C5 micro console has also played a large role in meeting basket weight restrictions, which vary on a global basis. The console weighs up to 35 pounds less than other options, and takes up much less space. In some cases, this will allow Skyline to fit multiple booms in one basket, even with lower weight limits.
“We want to control the limits when it comes to bringing bots out of controlled environments,” Bloom says.
To achieve this, we believe KUKA is the right automation supplier to partner with. They are ready to take robotics far beyond typical applications.”
All the technologies built into Ozmo are highly advanced, especially the world-class software and hardware components. It allows Skyline to not only control and adjust the robot’s movements in flight but also to stabilize – in real time – the system basket/platform on which the robot is riding.
What makes this so difficult is having to adapt to unforeseen variables such as wind gusts or crane malfunctions, which can cause one side of the basket to sink more than the opposite end.
Ozmo can address all of these variables and compensate on the spot to ensure the quality of cleaning and the most efficient descent path to do so.
To achieve stability, Ozmo uses KUKA’s robot arm itself as a way to apply a counterforce to an unstable basket. The robot arm remains facing the building window for an additional half-second to prevent the basket from shaking. According to Blum, Skyline is the first and only robotics company to successfully use a robotic arm in this way.
“A lot of robotics companies want to get into the robotic window cleaning business,” says Michael Brown, Chairman and CEO of Skyline Robotics.
However, the fact of the matter is that doing so is very complex and mathematical, especially in terms of artificial intelligence and machine learning. You can’t just slap a robot into a basket and think that’s all there is to it.
“We’ve worked with window washers for years to perfect our system and make sure it contains the necessary algorithms for all possible variables.”
Brown also notes that partnerships have been central to Ozmo’s development. “Koka has been advising us every step of the way, and we really couldn’t have asked for a better partner.
“Once we have completed what I call the proof-of-concept stage in New York City, we plan to re-meet with Kuka to discuss and gain insight into how we can modify or improve our product using their technology. For us, the collaboration with Kuka is critical to the success of our business.”
You may also like…
#Skyline #Robotics #industrial #robot #Kuka #clean #skyscraper #windows