Researchers at MIT have built a system that displays an autonomous robot’s path planning options, as the bot considers its route. The system was designed in response to visitors of the school’s Aerospace Control Lab who often thought the robots were simply displaying random behaviors.
“Normally, a robot may make some decision, but you can’t quite tell what’s going on in its mind — why it’s choosing a particular path,” Ali-akbar Agha-mohammadi, a post doctoral student at MIT’s Aerospace Controls Lab. “But if you can see the robot’s plan projected on the ground, you can connect what it perceives with what it does to make sense of its actions.”
To create the system, the researchers mounted 18 motion-capture cameras to the ceiling. Sensors were added to real robots so they could be easily tracked. Software was also created to display the trajectory of each robot, as well as the possible paths the primary robot of interest might take. The projections appear on the ground, as the robots roll or fly through the scene.
“As designers, when we can compare the robot’s perceptions with how it acts, we can find bugs in our code much faster,” Agha-mohammadi says. “For example, if we fly a quadrotor, and see something go wrong in its mind, we can terminate the code before it hits the wall, or breaks.”
The researchers hope their system will one day be used by companies to test their algorithms, before they are let loose in the real world.