In 1913, Henry Ford revolutionized automotive manufacturing with the first assembly line in motion, an innovation that has made rebuilding new vehicles faster and more efficient. A few hundred years later, Ford use now artificial intelligence to accelerate the speed of today production lines.
AT Ford transmission factory in Livonia, Mich., the station where robots help assemble torque converters now includes a system that uses AI to learn from previous attempts how to move parts in place most efficiently. Inside a large safety cage, the robot’s arms rotate around grabbing circular pieces of metal, each about the diameter of a plate, from a conveyor and slitting them together.
Ford uses technology from a startup called Symbio Robotics which examines the last hundreds of attempts to determine which approaches and movements have appeared to be the most effective. A computer sitting just outside the cage shows Symbio’s technology that senses and controls the arms. Toyota and Nissan use the same technology to improve the efficiency of their production lines.
The technology allows this part of the assembly line to run 15% faster, a significant improvement in automotive manufacturing where low profit margins are heavily dependent on manufacturing efficiency.
“Personally, I think it will be something of the future,” says Lon Van Geloven, production manager at the Livonia plant. He says Ford plans to study the advisability of using the technology in other factories. Van Geloven says the technology can be used anywhere a computer can learn by feeling how things fit together. “There are many applications,” he says.
AI is often seen as a disruptive and transformative technology, but the configuration of the Livonia couple illustrates how AI can creep into industrial processes in a gradual and often imperceptible way.
Automotive manufacturing is already highly automated, but the robots that help assemble, weld and paint vehicles are essentially powerful and precise automatons that repeat the same task over and over again but have no ability to understand or react to them. environment.
Adding more automation is a challenge. Tasks that remain out of reach of machines include tasks such as feeding flexible cables through the dashboard and body of a car. In 2018, Elon Musk blamed Tesla Model 3’s production delays on the decision to rely more on automation in the making.
Researchers and startups are exploring ways for AI to empower robots, for example by allowing them to perceive and grasp even unfamiliar objects moving along the conveyor belts. Ford’s example shows how existing machines can often be improved by introducing simple sensing and learning capabilities.