ABB Robotics launches AI Robot Trainer in Fashion Inductor module

The company says the addition can cut engineering and commissioning effort by up to 75 % for system integrators. The platform uses pre‑trained, fashion‑specific vision models and a closed‑loop retraining workflow that monitors robot performance, generates new training data and deploys improvements back to the robot.

Throughput of up to 1,300 items per hour per cell and picking accuracy above 99.5 % are claimed, with a digital twin added to accelerate commissioning and enable third‑party component integration. ABB says the solution will expand to other vision‑based applications by Q1 2027.