The Cheetah 3 robot developed by engineers at the MIT can now leap and gallop across rough terrain, climb a staircase littered with debris, and quickly recover its balance when suddenly yanked or shoved, all while essentially being blind.
Described as “blind locomotion”, the 90-pound mechanical beast is intentionally designed to do all this without relying on cameras or any external environmental sensors.
The design may also be used for exploring disaster zones and other dangerous or inaccessible environments and versatile tasks such as power plant inspection, the researchers said.
“There are many unexpected behaviours the robot should be able to handle without relying too much on vision,” said Sangbae Kim, Associate Professor and robot’s designer at the Massachusetts Institute of Technology (MIT) in Boston.
“Vision can be noisy, slightly inaccurate, and sometimes not available, and if you rely too much on vision, your robot has to be very accurate in position and eventually will be slow.
“So we want the robot to rely more on tactile information. That way, it can handle unexpected obstacles while moving fast,” Kim said.
The Cheetah 3 nimbly “feels” its way through its surroundings using two new algorithms — a contact detection algorithm and a model-predictive control algorithm.
While the contact detection algorithm helps the robot determine the best time for a given leg to switch from swinging in the air to stepping on the ground, the model-predictive control algorithm predicts how much force a given leg should apply once it has committed to a step.
These algorithms are designed to make these calculations for each leg every 50 milliseconds, or 20 times per second.
The findings will be presented at the International Conference on Intelligent Robots, in Madrid.
Compared to its predecessor Cheetah 2, the robot’s improved hardware also includes an expanded range of motion that allows the robot to stretch backwards and forwards, and twist from side to side, much like a cat limbering up to pounce, the researchers said. IANS
