The visionless “ Cheetah 3 ” can jump across rough terrain, climb staircase littered with garage, leap on wooden blocks, and quickly get back on its four legs when shoved with an unexpected force.
Many robots depend on cameras and other visual sensors to find their way around the world. However, that is not always realistic — it can be too dark, too chaotic or even play tricks. MIT’s 90-pound Cheetah can track you in rough terrains without needing a vision camera or any environmental sensors.
Even without cameras to dodge obstacles by sight, the 90-pound robot is equipped with new algorithms that help it navigate its environment by touch. The latest innovation works on the “contact detection” algorithm developed by the researchers. The algorithm uses data from gyroscopes, accelerometers, and positions of the leg to determine the probabilities of different scenarios–like leg making contact with the ground or force generated one it hits the ground, analyzing whether to swing or step.
How it Works?
If Cheetah steps on an unexpected obstacle, it can determine whether each leg should push down or lift away. The second algorithm, meanwhile, predicts the positioning of robot so that it can quickly react to its situation. Even if you push the robot around, it will know how to get back on track. Researchers at MIT are persistently trying to achieve a next-generation robotic quadruped, which would help people in achieving difficult tasks.
“I think there are countless occasions where we [would] want to send robots to do simple tasks instead of humans. Dangerous, dirty, and difficult work can be done much more safely through remotely controlled robots,” said Kim. That could make it useful for power plant inspections, remote rescues and other dangerous situations where there is no help if a robot gets stuck or falls over.
MIT does not expect robots to rely exclusively on this technology. Most likely, it would be used as a backup for moments when a robot either cannot see properly or hits an obstacle it was not expecting.