Micropsi Industries
Canvas Category Software : Operational Technology : Industrial Robot
Micropsi Industries develops software for robots. Our product, MIRAI, enables industrial robots to handle variance in production. MIRAI-powered robots use cameras and sensors to react in real time to dynamic conditions in a workspace.
Assembly Line
How to Train a MIRAI Positioning Skill
Micropsi Industries’ AI-Powered Robot Controller Is Now Hardware Agnostic
Micropsi Industries’ artificial intelligence-powered robot control software MIRAI, which helps automate complex tasks too difficult or costly to automate with traditional programming, will soon be accessible for all robot users. Previously compatible exclusively with Universal Robots and FANUC robots, MIRAI will be available for KUKA robots in early Q4, followed by other collaborative robots (cobots) and industrial robots as requested.
Using AI, MIRAI generates robot movements directly and in real time. Robot skills (or specific tasks) are trained, not programmed, in a few days through human demonstration, without users needing programming or AI knowledge. To start, the robot is repeatedly shown both a task and the environment with the help of a camera that is typically mounted on the robot’s wrist. The recorded movements are then transformed into a skill capable of handling variances and dynamic environmental conditions.
Automate the Impossible: MIRAI-Powered FANUC Robots Master Cable Plugging
Robots Handling Cables?! Automated Cable Applications with MIRAI
Micropsi raises $30M to retrain industrial robots using human demonstrations
Micropsi claims that, using AI, MIRAI can generate robot movements in real time — dealing with variations in position, color, and lighting conditions. It can also be trained and retrained for various process steps, the company says, including detecting leaks in machinery, screwing screws and inserting cables into products, and sorting objects on the assembly line.
“Data is generated by giving demonstrations, the rest is done by MIRAI in the background — it takes [about] 30 minutes of demonstrations and between one and three hours of number-crunching time in the cloud to create a new skill from scratch,” Vuine explained. “Users learn how to create good datasets by iterating their skills: Record some data, see the robot perform, add some more data to address weaknesses, and after three or four iterations, a very robots skill has been created. No one at Micropsi Industries needs to understand the use case, and no one on the customer side needs to understand the machine learning.”