New MIT algorithm optimizes sensor placement on soft robots to help them understand the world

Soft robots can be far more flexible than their rigid relatives, but their vast ranges of motion makes it hard to map the location of their body parts. A new algorithm could give them greater control of their movements by optimizing the arrangement of sensors on their bodies. “You can’t put an infinite number of sensors on the robot itself,” said study co-lead author Andrew Spielberg, a PhD student at MIT CSAIL. “So, the question is: how many sensors do you have, and where do you put those sensors in order to get the most bang for your buck?” The researchers developed a novel neural…

This story continues at The Next Web