AIVEX Brings Physical AI Into Korean Battery-Plant Packaging Work
AIVEX said its AIbot platform automated a crucible packaging-removal process at a leading Korean battery-materials company. The system combines AI vision, 3D optics, 6D pose estimation and automatic path planning to handle irregular ropes and wrapping film. The deployment points to physical AI moving into factory tasks that are repetitive but too variable for simple fixed automation.
What happened
AIVEX, a Korean industrial physical AI company, said it has deployed an unmanned automation system for a packaging-removal process at a leading domestic battery-materials company.
The project targets crucible pallets used in cathode-material production, where wrapping film and ropes must be removed before the next manufacturing step.
The company said its AIbot robotics control platform recognizes ropes, detects joints, identifies vertical rope direction, locates support pieces, corrects crucible-position deviations, creates wrapping-cut paths and checks the result after cutting.
AIbot is described as a ROS2-based platform using 2D and 3D hand-eye optical systems, Nvidia Jetson PCs, AI models, 6D pose estimation, automatic robot-path generation and device communication.
Why it matters
The signal is not just another factory robot installation.
AIVEX is presenting the project as a physical AI use case for irregular, mixed-material work that fixed automation has struggled to handle.
The source says crucible pallets were previously difficult to automate because product positions were inconsistent and rope count, placement and direction varied by pallet.
That matters for manufacturers because many packaging and logistics tasks are repetitive but not perfectly structured.
If AI vision and cycle-by-cycle path planning can handle those variations, more factory workflows could move from manual handling toward unmanned operation, although adoption would still depend on site conditions and economics.
Who is affected
The immediate customer is an unnamed Korean battery-materials company.
AIVEX said the deployment achieved 100 percent unmanned automation for the crucible packaging-removal process, enabled 24-hour continuous operation, reduced worker safety accidents to zero and kept takt time within 14 minutes.
AIVEX handled vision recognition, AI-based judgment and automatic path generation.
A partner managed the robot hardware, gripper and overall equipment project management.
What to watch next
The next question is whether similar requests from other customers turn into repeat deployments.
AIVEX said it is receiving more inquiries for comparable projects and plans to expand the solution to pallet-based packaging logistics across manufacturing sites.
Readers should also watch whether physical AI platforms can keep performance stable when lighting, material transparency and object placement change.
AIVEX said it used 3D optics, AI algorithms and its own AI network to recognize translucent ropes, boxes and wrapping film with a limited number of training images.
