Leave it to MIT to build a robot that collaborates with others in a controlled environment.
On Wednesday, MIT announced some of its researchers attending the Institute for Electrical and Electronics Engineers’ International Conference on Robotics and Automation were nominated for best-paper awards for developing a new algorithm that drastically cuts the time it takes for a robot to plan.
“We’re really excited about the idea of using robots in more extensive ways in manufacturing,” says Daniela Rus, the Andrew and Erna Viterbi Professor in MIT’s Department of Electrical Engineering and Computer Science, whose group developed the new algorithm. “For this, we need robots that can figure things out for themselves more than current robots do. We see this algorithm as a step in that direction.”
As you can see in the video above, three of the robots, so long as they’re programmed to know exactly where specified objects are, are able to assemble a simple chair together. Most of the time spent by the robots is determining how best to go about grasping individual pieces of the chair.
But it cycles through the easiest grasp positions before considering the more difficult which means it can be interrupted by a variable and continue its task.
“Our solution considers a multiple-step assembly operation and optimizes how the robots place themselves in a way that takes into account the entire process, not just the current step,” said Rus.
In addition to their experiments with real robots, the researchers also ran a host of simulations involving more complex assembly operations. In some, they found that their algorithm could, in minutes, produce a workable plan that involved just a few drops, where the optimal solution took hours to compute. In others, the optimal solution was intractable — it would have taken millennia to compute. But their algorithm could still produce a workable plan.