Lockheed, Xaba test AI-driven robots to improve airframe manufacturing
By DE Staff
Automation Machine BuildingToronto-based Xaba’s xCognition improves robotic accuracy and consistency by more than ten times, companies say.
(Photo credit: Getty Images)
Lockheed Martin and Toronto-based Xaba, developer of an AI-driven robotics and CNC machine controller, announced the completion of a collaboration that combined the aerospace company’s industrial robots with Xaba’s physics-informed AI neural network model, xCognition.
According to Xaba, xCognition employs “industrial AI” that differs from predictive AI in that it focuses on the physical world. As a result, any industrial robot can be made autonomous with xCognition, in that robotic system can generate its own programs and execute tasks such as welding, drilling, assembling and additive manufacturing.
This capability is of particular interest to aerospace companies that have struggled to integrate robotics into manufacturing processes like drilling, laser welding, light machining, and precise assembly. According to Xaba, this has been due to a lack of the robotics intelligence required by the aerospace industry to meets its requirements for accuracy, repeatability, and to work in path programming mode rather than point-to-point.
To test the AI system, the Lockheed and Xaba teams focused on the kind of robotic work cell used in a typical aerospace factory to see if xCognition could improve a commercial robot’s ability to carry out an assigned task.
The first phase of the test assessed the robot’s performance in maintaining accurate and consistent trajectory positioning with and without Xaba’s xCognition. The second phase required the robot to perform drilling tests on an aluminum test plate with specific positional tolerances. According to the Lockheed Martin and Xaba, xCognition improved accuracy and consistency of the commercial robot by 10 times.
“The accuracy performance of a robotic system limits the type of process it can perform based on the cost efficiency of the accuracy hardware,” said Matthew Galla, applications engineer staff for Lockheed Martin’s aeronautics business. “The test with the xCognition controller allows us to rethink how we can accelerate innovation in manufacturing.”
xaba.ai
