Automation ABB Robotics Brings Physical AI to Fashion Logistics

From Sariana Kunze 2 min Reading Time

Related Vendors

ABB Robotics has launched its first fully integrated, camera-based Physical AI solution for logistics applications in the fashion industry.

ABB Robotics is launching its first end-to-end physical-AI solution for industrial applications: the Fashion Inductor and AI Robot Trainer.(Image:  ABB Robotics)
ABB Robotics is launching its first end-to-end physical-AI solution for industrial applications: the Fashion Inductor and AI Robot Trainer.
(Image: ABB Robotics)

By integrating the AI Robot Trainer into the Fashion Inductor feature package, ABB Robotics aims to help system integrators implement, scale, and continuously optimize AI-powered applications for fashion logistics with less effort and risk.

“Physical AI is fundamentally changing what robots can do in industrial applications,” emphasizes Craig McDonnell, head of the Industries business line at ABB Robotics. “Some of the greatest potential of Physical AI lies in applications that, due to their high variability, have been difficult to automate until now.”

Designed to Meet the Demands of Fashion Logistics

The Fashion Inductor was developed specifically to meet the demands and accommodate the wide variety of the fashion and apparel logistics sector, where products, packaging, and operating conditions are constantly changing. Even today, the system is designed to enable high-performance sorting and separation under real-world logistics conditions—with a throughput of up to 1,300 items per hour per cell and a grasping accuracy of more than 99.5 percent. This is made possible by ABB Robotics’ AI-powered automatic path planning, the robots’ high motion precision, and the image processing technology developed specifically for this application.

Physical AI Features Reduce Effort by 75 Percent

The AI Robot Trainer adds camera-based Physical AI features designed to reduce development and commissioning efforts by up to 75 percent. The solution includes pre-trained AI models for image processing—specifically tailored to applications in fashion and apparel logistics—as well as application-specific tools and features for quickly retraining the models. This is intended to enable system integrators to implement applications without specialized AI expertise, adapt them to changing requirements, and continuously optimize them.

AI Robot Trainer Enables a Closed-Loop Workflow

The AI models are not only developed but also continuously optimized throughout the robot system’s entire lifecycle and adapted to real-world performance requirements and changing operating conditions. The AI Robot Trainer enables fast and structured retraining tailored to the specific robot cell within a so-called closed-loop workflow. In this process, the system monitors the robot’s performance, detects deviations, generates new training data for the models, and feeds improvements directly back to the robot.

Subscribe to the newsletter now

Don't Miss out on Our Best Content

By clicking on „Subscribe to Newsletter“ I agree to the processing and use of my data according to the consent form (please expand for details) and accept the Terms of Use. For more information, please see our Privacy Policy. The consent declaration relates, among other things, to the sending of editorial newsletters by email and to data matching for marketing purposes with selected advertising partners (e.g., LinkedIn, Google, Meta).

Unfold for details of your consent