Robot dog learns to walk in one hourVirtual spinal cord is continuously optimized
Date: July 18, 2022
Source: Max Planck Institute for Intelligent Systems
Summary: Like a newborn animal, a four-legged robot stumbles around during its first walking attempts. But while a foal or a giraffe needs much longer to master walking, the robot learns to move forward fluently in just one hour. A computer program acts as the artificial presentation of the animal's spinal cord, and learns to optimize the robot's movement in a short time. The artificial neural network is not yet ideally adjusted at the beginning, but rapidly self-adjusts.
A newborn giraffe or foal must learn to walk on its legs as fast as possible to avoid predators. Animals are born with muscle coordination networks located in their spinal cord. However, learning the precise coordination of leg muscles and tendons takes some time. Initially, baby animals rely heavily on hard-wired spinal cord reflexes. While somewhat more basic, motor control reflexes help the animal to avoid falling and hurting themselves during their first walking attempts. The following, more advanced and precise muscle control must be practiced, until eventually the nervous system is well adapted to the young animal's leg muscles and tendons. No more uncontrolled stumbling -- the young animal can now keep up with the adults.
Researchers at the Max Planck Institute for Intelligent Systems (MPI-IS) in Stuttgart conducted a research study to find out how animals learn to walk and learn from stumbling. They built a four-legged, dog-sized robot, that helped them figure out the details.
"As engineers and roboticists, we sought the answer by building a robot that features reflexes just like an animal and learns from mistakes," says Felix Ruppert, a former doctoral student in the Dynamic Locomotion research group at MPI-IS. "If an animal stumbles, is that a mistake? Not if it happens once. But if it stumbles frequently, it gives us a measure of how well the robot walks."
Felix Ruppert is first author of "Learning Plastic Matching of Robot Dynamics in Closed-loop Central Pattern Generators," which will be published July 18, 2022 in the journal Nature Machine Intelligence.
* * *
Source:
https://www.sciencedaily.com/releases/2022/07/220718122229.htm
