Micropsi Industries (Berlin, Germany) presents its latest version of MIRAI robot control system. Using artificial intelligence, MIRAI enables robots to flexibly react to variances in their tasks in real time by learning from humans.
MIRAI's new "positioning skills" feature allows it to give examples of quality movements to the robot and the robot generalizes and understands what to do quickly.
The result is set-up times at about three hours. Robot speeds also increased to enable shorter cycle times.
With MIRAI, preparing robots to perform tasks that include variances requires a human worker to guide the robot arm several times through typically occurring scenarios to show the robot to its destination.
A machine-learning process then derives a motion intuition for the robot from the given examples. To teach a robot to find the destination, a human worker needs to show MIRAI the surroundings of the target with the camera. The robot then independently searches for the shortest path to the object.
Through demonstrations, the robot can learn almost any task, including all precise tasks that involve variances, whether tracing lines, bolting differently placed screws or checking solder joints at varying positions.
Robots can perform tasks sooner and manufacturers save on engineering and hardware costs. MIRAI-supported robots have a return-on-investment (ROI) of less than 12 months.