 |
| Ford's smarter robots are speeding up assembly lines |
In 1913, Henry Ford revolutionized the automobile industry with the first mobile assembly line, an innovation that made assembly of new cars faster and more efficient.
Nearly a hundred years later, Ford is using artificial intelligence to accelerate existing product lines.
The Ford Robot Factory in Michigan (where robots help assemble a torque converter) now includes a system that uses artificial intelligence to learn from past attempts about how to assemble parts together more efficiently.
Ford is using technology from a startup called Symbio Robotics to detect and control arm. Hundreds of past attempts are examined to determine which techniques and movements appear to be the most effective.
Toyota and Nissan are using the same technology to improve the efficiency of their production lines.
Technology has increased the speed of this segment of the assembly line by 15%, which is a major feat in the automotive industry where carmakers' meager profit margins depend largely on production efficiency.
The company plans to check whether it will adopt the technology in other factories, as the technology can learn in the sense that computers can learn well in all aspects, and there are many uses for that.
AI is widely seen as a transformative technology, but the assembly of torque converters at the Ford plant illustrates how AI can gradually and often imperceptibly penetrate industrial processes.
Although the automotive industry is already highly automated, the robots that help assemble, weld, and paint vehicles are powerful and accurate machines that can do the same tasks endlessly without understanding or interacting with the environment.
Adding more automation is challenging, and machines are still unable to do the tasks including adding tasks like adding flex cables across the dashboard and body of the car.
In 2018, Elon Musk blamed the decision to increase automation in manufacturing, leading Tesla to delay production of the Model 3.
Researchers and startups are looking for ways to give robots more jobs, for example to perceive and understand UFOs moving along conveyor belts.
Ford's example shows how often existing machines need improvement with simple discovery and learning functions.
As computer vision algorithms can be trained to find defects in products or problems in production lines, artificial intelligence is increasingly being used for quality control in manufacturing.
One of the biggest challenges is that each manufacturing process is unique and requires a certain automation. Additionally, new technologies must be integrated into the workflow without affecting productivity.