MIT’s 90-pound mechanical beast can track you in rough terrains without needing a vision camera or any environmental sensors.
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.
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. Robotics designer Sangbee Kim puts it in simple words: “When is a safe time to commit my footstep.”
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.
The researchers tested the robot, which behaves like a full grown Labrador, on the different parameter and even on the filed. In a video by MIT, the robot can be seen doing kee joints, slow trot walks and bounding on a treadmill. The robot climbs on wooden stairs, losing balance in its second attempt, but quickly regains control.
Although, the team has installed cameras for mapping the general environment, informing when faced with large obstacles like closed doors but the team’s major focus is the “blind locomotive.”
“What if it steps on something that a camera can’t see? What will it do? That’s where blind locomotion can help. We don’t want to trust our vision too much,” said the team.