De-nest and present fragile filled glass vials/syringes for visual inspection
Parenteral products require 100% inspection, so filled glass vials and prefilled syringes must be de-nested from trays, gently handled, oriented/rotated for camera and leak (CCIT) inspection, and re-nested or rejected. The objects are thin-walled glass containing finished sterile drug product, fragile and slippery when siliconized, and present in high throughput (Merck's lines run very large vial/syringe volumes for Keytruda and Gardasil). The task sits at the finish stage between sealing and secondary packaging. It is hard for a robot because grip force must be modulated per fragile container to avoid chipping or glass-to-glass contact, and a dropped or cracked unit is destroyed product plus a potential contamination event. Merck runs automated inspection on these lines, but evidence is for machine-vision inspection rather than dexterous robotic handling, so the contact-rich handling need is inferred. We identified this through our own research; we have not confirmed the specifics with the customer directly. This page is our researched read — a starting point for that conversation.
What the task is
RESEARCHED · our reconstructionParenteral products require 100% inspection, so filled glass vials and prefilled syringes must be de-nested from trays, gently handled, oriented/rotated for camera and leak (CCIT) inspection, and re-nested or rejected. The objects are thin-walled glass containing finished sterile drug product, fragile and slippery when siliconized, and present in high throughput (Merck's lines run very large vial/syringe volumes for Keytruda and Gardasil). The task sits at the finish stage between sealing and secondary packaging. It is hard for a robot because grip force must be modulated per fragile container to avoid chipping or glass-to-glass contact, and a dropped or cracked unit is destroyed product plus a potential contamination event. Merck runs automated inspection on these lines, but evidence is for machine-vision inspection rather than dexterous robotic handling, so the contact-rich handling need is inferred.
Is this the actual task and sequence? What are the real tolerances, cycle rate, and reject criteria, and which steps are today's manual bottleneck? Answering these is what turns this from a researched signal into a validated use case.