A new algorithm could make robots safer by making them more aware of human inattention.
In computerized simulations of packaging and assembly lines where humans and robots work together, an algorithm designed to account for human carelessness increased efficiency by as much as 80% and about 38% over existing methods.
I have a job report. IEEE Transactions on Systems Man and Cybernetics Systems.
“Every day there are a large number of accidents that are caused by carelessness — most of them, unfortunately, human error,” said Mehdi Hussainzada, assistant professor at Washington State University's School of Mechanical and Materials Engineering. Because of”. “Robots work according to plans and follow rules, but humans often don't. This is the most difficult and challenging problem.”
Robots working alongside people are increasingly common in many industries, where they often work together. Many industries require humans and robots to share a workspace, but repetitive and tedious work can cause people to lose focus and make mistakes. Most computer programs help robots when something goes wrong. Hussainzada said those algorithms can focus on improving either efficiency or safety, but they haven't considered the changing behavior of the people they're working with.
As part of their effort to develop a plan for the robots, the researchers first worked to assess human inattention, looking at factors such as how often a human ignores a safety alert or He misses it.
“We defined carelessness and the robot observed human behavior and tried to understand it,” he said. “The concept of levels of carelessness is a new one. If we know which person is careless, we can do something about it.”
Once the robot detects careless behavior, it is programmed to change how it interacts with a human acting in that way, working to reduce the chance of it happening. That the person may make a mistake in the workplace or harm themselves. So, for example, a robot can change the way it manages its tasks to avoid getting in the way of a human. The robot constantly updates the carelessness level and any changes it observes.
The researchers tested their plan with a computer simulation of a packaging line consisting of four people and a robot. They also tested an artificial collaborative assembly line where two humans would work together with a robot.
Hussainzada said the basic idea is to make the algorithm less sensitive to careless human behavior. “Our results show that the proposed scheme has the potential to improve efficiency and safety.”
After conducting computerized simulations, the researchers plan to test their work with real robots and people in the laboratory and eventually in field studies. They also want to quantify and account for other human traits that affect workplace productivity, such as human rationality or risk awareness.
The work was funded by the National Science Foundation. Co-authors of the study included Bruno Sinopoli and Aaron F. Bobak from Washington University, St. Louis.