{"id":16064,"date":"2022-08-15T00:00:00","date_gmt":"2022-08-14T22:00:00","guid":{"rendered":"https:\/\/c01.purpledshub.com\/bbcsciencefocus\/?post_type=purple_issue&p=16064"},"modified":"2022-08-22T11:35:44","modified_gmt":"2022-08-22T09:35:44","slug":"robot-dog-learns-to-walk-by-stumbling-just-like-young-animals-in-the-wild","status":"publish","type":"post","link":"https:\/\/c01.purpledshub.com\/bbcsciencefocus\/2022\/08\/15\/robot-dog-learns-to-walk-by-stumbling-just-like-young-animals-in-the-wild\/","title":{"rendered":"Robot dog learns to walk by stumbling, just like young animals in the wild"},"content":{"rendered":"\n

ROBOT DOG LEARNS TO WALK BY STUMBLING, JUST LIKE YOUNG ANIMALS IN THE WILD <\/h3>\n\n

When this robot gets knocked down, it gets up again <\/p>\n\n

Morti, a robot dog, has taught itself to walk, just one hour after taking its first step. It learned just like animals in the wild: by tripping and stumbling until it understood how to balance on its limbs. <\/p>\n\n

Morti was developed by researchers at the Max Planck Institute for Intelligent Systems as a way for scientists to closely study how animals learn to walk. <\/p>\n\n

\"\"
Morti the robot dog taking tentative steps on the treadmill <\/figcaption><\/figure>\n\n

With Morti, researchers could measure the forces, torques and muscle power of each limb \u2013 something that would\u2019ve been much more difficult to do in a live organism, said Felix Ruppert, a PhD student and first author of the new study.<\/span><\/p>\n\n

In building the Labrador-sized bot, Ruppert and the team first needed to computerise the mechanism by which animals and humans learn to walk. <\/p>\n\n

Walking, like blinking and breathing, are rhythmic tasks because they use the same muscle movements repeated throughout the activity. These tasks aren\u2019t coordinated in the brain, but are controlled by networks of neurons, collectively called a Central Pattern Generator (CPG). Our CPG for walking is found in our spinal cord, as this is what controls the muscle contractions in our legs that take us forward, one step at a time. When we trip or stumble over rough terrain, we don\u2019t immediately stop walking. This is because the spinal CPG can control our legs\u2019 reflexes without needing to check with the brain about how to proceed. Morti therefore had to be given an algorithm that acted like a spinal cord. With its basic CPG in place, Morti was put on the treadmill. At this point, Morti had no idea how to walk, nor any way to tell what space it was in or how far to stretch out one leg before putting it down to lift the other. It was as uncoordinated as Bambi.<\/span><\/p>\n\n

\u201cThe computer produces signals that control the legs\u2019 motors, and the robot initially walks and stumbles. Data flows back from the sensors [in the robot\u2019s feet] to the virtual spinal cord where sensor and CPG data are compared. If the sensor data does not match the expected data, the learning algorithm changes the walking behaviour until the robot walks well, and without stumbling,\u201d said Ruppert. <\/p>\n\n