In the past few years, we have covered plenty of robots that can handle objects of all shapes and sizes. With deep learning, robots are going to become even more capable in this area. UC Berkeley engineers have created new software that combines neural networks with motion planning software to give robots the ability to grasp and smoothly move objects.
As the researchers explain:
“The neural network takes only a few milliseconds to compute an approximate motion. It’s very fast, but it’s inaccurate. However, if we then feed that approximation into the motion planner, the motion planner only needs a few iterations to compute the final motion.”
By combining the neural network with the motion planner, computation time was cut from 29 seconds to 80ms.