Cleaning windows of high-rise buildings is definitely among the toughest jobs in the world. Besides being in danger up there, the wind blows harder and the heat is also extreme as the sun is reflecting on the windows. „You literally feel like you’re in an oven” as Michael Brown, CEO of Skyline Robotics puts it. To save lives and also get the job done, the TelAviv-based company teamed up with KUKA Robotics and developed the world’s first high-rise window-cleaning robot.
The “dirty, dull and dangerous” job of cleaning steel and glass skyscrapers has cost thousands of lives, according to Michael Brown, CEO & Chairman of Skyline Robotics, based in Tel Aviv. “The problem, put simply, is that cleaning windows at height is extremely dangerous.”
The idea of a window-cleaning robot came when he was driving in New York City with its tremendous number of tall buildings. “I said to myself, I cannot believe people are still cleaning windows by hand. Why are they not using robots?” – he recalls to NoCamels.
He teamed up with Avi Abadi, founder of Skyline Robotics in 2017, who had already developed a prototype of the technology using lidar camera (light detection and ranging) and force sensors to scan building surfaces, memorizing every curve and edge, along with advanced algorithms to calculate optimal cleaning paths.
Ozmo saves lives, works times faster and never misses a spot
Companies have experimented with automated window cleaning solutions, but they often failed in terms of actually getting the windows clean. Another obstacle was that these devices were designed for buildings of 10 stories, no higher. It was Skyline Robotics who – after 5 years of development – created the world’s first high-rise robot window cleaner: Ozmo.
“The robot can clean three to four times quicker than a human, doesn’t need to go to the bathroom, and doesn’t need to take a break. It can also do night cleaning,” – says Brown, adding: „As for the human window cleaners, there are plenty of employment opportunities for them to control the robots, move them between locations, or redeploy them.”
The technology that makes Ozmo see, feel and think
Ozmo is a system that combines KUKA’s KR AGILUS robot arm with a computerized vision system, artificial intelligence (AI) and machine learning technologies. In order to provide power and water, Ozmo is designed to fit into a building’s existing building maintenance unit (BMU) infrastructure, gathering the power and water supply from the building itself. Within the basket a table houses several types of sensors and computers. The robotic arm and its Lidar (light detection and ranging) camera, which uses lasers for imaging, sit on top of the table. Once the table is clamped into a building’s preexisting window-washing basket, the system is ready to work – KUKA Robotics explains the details.
Ross Blum President and COO of Skyline Robotics uses analogies to the human senses when describing Ozmo’s characteristics: “The robot arm communicates to the Lidar camera that provides ‘sight’ for the robot and to a force torque sensor at the end of the cleaning brush that gives Ozmo the sense of ‘touch’”. The system software acts as the brain and collects data from several different cameras and sensors to continually optimize the path planning at a rate of about 200 times/second while automating Ozmo’s descent down the glass facade of a skyscraper.
“A lot of robotics companies want to get into the automated window cleaning business,” – says Michael Brown. “The truth of the matter, however, is that doing so is very complex and mathematical, especially in terms of AI and machine learning. You can’t just slap a robot in a basket and think that’s all there is to it. We’ve been working with window washers for years to perfect our system and ensure that it has the necessary algorithms to account for variable environments.”
There is more to come
For the future, Skyline is looking to make the most of its robots, by getting them to check buildings’ façades for damage, leaks, broken windows and any other maintenance issues. There are also plans to adapt the robots so they can clean ships, aeroplanes, or any other large or challenging structure.
Photo, video: kuka.com, skylinerobotics.com, nocamels.com