MIT researchers have developed an algorithm that they say will enable robots to learn and adapt to humans so they can soon work side-by-side on factory floors.
Traditionally, robots working in factories are large, imposing and sectioned off in metal cages as they move heavy loads and perform menial, repetitive tasks.
However, Julie Shah, the Boeing Career Development Assistant Professor of Aeronautics and Astronautics at MIT, said robots can be more than they've been in a manufacturing setting. It's time for robots to begin working more closely with humans, making workers jobs' safer and easier.
Shah, in a statement, said this is especially true in the airplane manufacturing industry.
"If the robot can provide tools and materials so the person doesn't have to walk over to pick up parts and walk back to the plane, you can significantly reduce the idle time of the person," said Shah, who leads the Interactive Robotics Group in MIT's Computer Science and Artificial Intelligence Laboratory.
"It's really hard to make robots do careful refinishing tasks that people do really well. But providing robotic assistants to do the non-value-added work can actually increase the productivity of the overall factory."
However, one of the issues involved with having humans work individually with robots is that every person works differently, and the robots will have to adapt to each worker.
To address that problem, Shah and her research team at MIT created an algorithm that enables robots to quickly learn an individual's preference for a certain task, and adapt accordingly to help complete the task. If the robot can learn and adjust quickly, it can move seamlessly from working with one worker to another.
Researchers are using the algorithm to train robots to work with humans, according to MIT. Shaw and her team are scheduled to present their findings at the Robotics: Science and Systems Conference in Sydney in July.
"It's an interesting machine-learning human-factors problem," Shah said. "Using this algorithm, we can significantly improve the robot's understanding of what the person's next likely actions are."
Researchers used a computational model in the form of a decision tree. Each branch of the tree represents a choice that a mechanic might make. For instance, does the mechanic want to put one bolt in place and hammer it in, or does the worker want to put a row of bolts in place first and then hammer them in.
The robot is designed to learn as it works, picking up on the mechanic's personal preferences.
At a robotics symposium in Cambridge, Mass. last fall, an MIT economist said robots and computers will soon replace humans in many mid-level jobs. Enough of these jobs will be replaced that it will transform the economy.
"What we're finally seeing is that our digital helpers aren't just catching up to us, but, in some cases, are passing us," said Andrew McAfee, an MIT economist and co-author of the book Race Against the Machine, in a panel discussion last October. "In some head-to-head contests, machines have raced past us."
In Shah's work, the robots are designed to work in concert with humans, taking on repetitive or more dangerous work.
Steve Derby, associate professor and co-director of the Flexible Manufacturing Center at Rensselaer Polytechnic Institute, said in a statement that MIT's algorithm moves the robotics industry closer to enabling a true collaboration between humans and robots.
"The evolution of the robot itself has been way too slow on all fronts, whether on mechanical design, controls or programming interface," Derby said. "I think this paper is important. It fits in with the whole spectrum of things that need to happen in getting people and robots to work next to each other."