Robots could become "smarter" by observing human movements.
The robots learn about human muscle movement through sensors, and then adjust their own motions to match this new information, a Georgia Tech University news release reported. The technique will be used to improve "time, safety and efficiency" in manufacturing plants.
Humans and robots often need to work together, such as when a person hangs a vehicle door on a hinge using a robotic lever.
"It turns into a constant tug of war between the person and the robot," Billy Gallagher, a recent Georgia Tech Ph.D. graduate in robotics who led the project, said in the news release. "Both react to each other's forces when working together. The problem is that a person's muscle stiffness is never constant, and a robot doesn't always know how to correctly react."
In the lever scenario, a person moves a lever and the robot moves accordingly; when the person stops and holds the lever in place they contract their arm muscles resulting in a co-contraction in the robot.
"The robot becomes confused. It doesn't know whether the force is purely another command that should be amplified or 'bounced' force due to muscle co-contraction," said Jun Ueda, Gallagher's advisor and a professor in the Woodruff School of Mechanical Engineering. "The robot reacts regardless."
This force creates a vibration which gets worse as the human continues to contract their muscles.
"You don't want instability when a robot is carrying a heavy door," Ueda said.
The researchers believe these dangerous forces can be eliminated if the operator were to wear sensors on their forearms, this allow the robot to "intelligently adjust" itself to suit the needs of the human.
"Instead of having the robot react to a human, we give it more information," Gallagher said. "Modeling the operator in this way allows the robot to actively adjust to changes in the way the operator moves."
"Future robots must be able to understand people better," Ueda said. "By making robots smarter, we can make them safer and more efficient."
WATCH:
