Researchers from the Max Planck Institute for Intelligent Systems in Suttgart, Germany, have managed to create a dog-sized robot that learned to walk in just one hour, a considerably faster learning time when compared to many newborn animals.
In order to learn so fast, the researchers created a computer program that acts as the artificial presentation of the animal's spinal cord. This computer program produces signals that control the legs motors. The data then flows back from the sensors to the virtual spinal cord, where the sensor and CPG data are compared. Based on this data, the computer program will then optimise the robots movement, thus speeding up the learning time.
RELATED: Newly Developed Robot Chef Learns To ‘Taste As You Go’
This rapid self-adjustment means that the robo-dog was able to walk in just one hour, a considerably amazing feat. However, this particular robot boasts other advantages when compared to ther similar robots in the industry.
When compared to other manufacturers, the Stuttgart model uses considerably less power and energy. This means that this particular robot is one of the most energy efficient out there.