Robots taught to walk and not fall
- December 2, 2022
- 0
Experts from the INRIA institute (France) have created an algorithm that helps the robot find a support point when it loses its balance. This was reported by the
Experts from the INRIA institute (France) have created an algorithm that helps the robot find a support point when it loses its balance. This was reported by the
Experts from the INRIA institute (France) have created an algorithm that helps the robot find a support point when it loses its balance. This was reported by the IEEE Spectrum magazine.
Based on the TALOS humanoid robot, scientists managed to produce an algorithm that allows the machine to maintain its balance while falling. As soon as the robot feels off balance, a special mechanism begins to look for a new support point.
According to the researchers, the task of not falling in case of loss of balance is quite simple and instinctive for humans. Enthusiasts noted that a person exposed a free limb during a fall and was leaning against a wall or other object. Humanoid robots do not have such mechanics.
As part of the experiment, the experts disabled one of the robot’s limbs, forcing them to come up with a solution to the problem. Experts noted that in three out of four cases, the car successfully activates the so-called D-Reflex and maintains its balance.
Source: Port Altele
John Wilkes is a seasoned journalist and author at Div Bracket. He specializes in covering trending news across a wide range of topics, from politics to entertainment and everything in between.