KUKA Robotics released iiQKA.AI Vision, an AI-powered software that simplifies industrial vision integration into robot automation systems through intuitive drag-and-drop configuration, edge computing on the KUKA AI Extension Platform, and secure local data processing without requiring cloud connections or specialized expertise.
- Supports 2D and 3D vision applications including bin picking, assembly, quality control, and depalletizing with drag-and-drop configuration
- Runs on edge computing directly in the KUKA controller using NVIDIA Jetson Orin module for low-latency AI inference
- All data processing is local—no cloud connection, external systems, or additional infrastructure required, ensuring high data security
- Configured entirely through KUKA's iiQWorks system with graphical user interface, pre-built templates, and guided workflows for efficient commissioning
- Automatically calculates precise gripper points and object orientation from image data or point clouds for seamless, reliable robotic processes
KUKA Robotics released its new iiQKA.AI Vision, an AI-powered software designed to fully integrate into the KUKA ecosystem for simple, fast commissioning.
The solution is particularly valuable for integrators and users with limited vision experience who want to efficiently integrate industrial vision into their automation solutions, without complex additional systems or high upfront costs.
Key takeaways:
· The intelligent software supports both 2D and 3D vision and enables typical applications such as bin picking, assembly, quality control, and depalletizing. With intuitive drag-and-drop configuration, users can quickly implement productive vision applications without specialized knowledge.
· For low-latency AI inference and secure, local data processing, the KUKA iiQKA.AI Vision’s image processing runs as edge computing directly in the controller on the KUKA AI Extension Platform, an integrated computing unit based on the NVIDIA Jetson Orin module. The system’s sufficient computing power supports demanding vision AI tasks without the added complexity that often comes with industrial image processing. No cloud connection, other external systems, or additional infrastructure is required.
· All data processing takes place locally within the system and images are processed and stored onboard. As a result, users benefit from high data security and independence from network connections.
· To support end-to-end workflow, the application is configured entirely in KUKA’s iiQWorks system via a standalone vision application with a graphical user interface. Drag-and-drop functionality, pre-built templates for typical applications and guided workflows support users from setup through commissioning, helping them implement vision applications efficiently. Robust image processing ensures process reliability with precise 2D and 3D object recognition, automatic orientation detection, and gripper point calculation.
· For object recognition in robust processes, the AI algorithms used in iiQKA.AI Vision precisely distinguish objects from the background and automatically calculate suitable gripper points. Precise positioning and gripper information are calculated based on image data or point clouds and transmitted directly to the robot, resulting in seamless, stable processes from detection to execution and consistently high image quality.
