Researchers at the Technical University of Vienna (TU Wien) have developed a self-learning robot capable of mimicking humans for simple tasks, such as cleaning washbasins.
This seemingly simple task is a huge challenge for robots. Traditional robot programming requires precise mathematical modeling of the complex curves of the washbasin, which is a time-consuming and complex task. The research team simplified this process by combining human demonstration and haptic data to train the robot to mimic human movements.
This learning method is not only suitable for household cleaning, but can also be applied to a variety of tasks in industrial production, such as polishing, painting, sanding, and gluing.
"It's relatively easy to capture the geometry of a washbasin with a camera," says Professor Andreas Kugi of the Institute for Automation and Control at the Technical University of Vienna, "but the key is to teach the robot how to choose the right way to move according to the different surfaces, and how fast it should be?" What is the right angle? What is the correct force? "
IT Home notes that this learning style is similar to the process of humans learning new skills, especially those that require hands-on hands.
"In the workshop, the master would instruct the apprentice to say, 'You need to press that narrow edge,"says Christian Hartl-Nesi, head of the Industrial Robotics Group at Andreas Kugi's team, "We wanted to find a way for the robot to learn in a similar way."
For this purpose, the research team developed a special cleaning tool, the sensor impregnation sponge. The sponge is used by the human "teacher" to repeatedly clean the leading edge of the sink through force sensors and tracking markers.
"We generate a lot of data with just a few demonstrations and then process it to help the robot understand the right way to clean," explains Christian Hartl-Nesi.
The research team then used an innovative data processing strategy that enabled the robot to effectively clean an entire sink or other object with complex surfaces, even if it had only been demonstrated how to clean one edge of the sink.
Christoph Unger, a PhD student in the Industrial Robotics Group, explains: "The robot has learned to adjust the way it grips the sponge according to the shape of the surface, as well as to apply different forces on tightly curved areas and flat surfaces. "
In the future, robots can be mounted on mobile platforms, making them powerful assistants in any shop floor environment. And just like humans, these robots can also pass on their own experience to other robots.