De-nest, handle and present filled glass vials/prefilled syringes for inspection
In Takeda's sterile fill-finish lines, filled primary containers (thin-walled glass vials, ampoules, and prefilled glass syringes) must be removed from their nests/trays and presented individually for visual inspection (particulates, cracks, fill level, cosmetic defects), then re-nested. The objects are fragile, slippery when wet/siliconized, and held to sub-millimeter pocket tolerances in nests. The task sits between filling/stoppering upstream and packaging/AVI downstream, and is high-volume parenteral output. It is hard for a robot because each pick must avoid glass-to-glass and glass-to-tool contact that chips or micro-cracks the container, while reliably seating the unit back into a tight nest pocket; vision alone cannot confirm a safe, non-damaging grasp. Industry inspection systems explicitly engineer their de-nest/inspect/re-nest handling to prevent glass-to-glass contact, underscoring the difficulty. 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 reconstructionIn Takeda's sterile fill-finish lines, filled primary containers (thin-walled glass vials, ampoules, and prefilled glass syringes) must be removed from their nests/trays and presented individually for visual inspection (particulates, cracks, fill level, cosmetic defects), then re-nested. The objects are fragile, slippery when wet/siliconized, and held to sub-millimeter pocket tolerances in nests. The task sits between filling/stoppering upstream and packaging/AVI downstream, and is high-volume parenteral output. It is hard for a robot because each pick must avoid glass-to-glass and glass-to-tool contact that chips or micro-cracks the container, while reliably seating the unit back into a tight nest pocket; vision alone cannot confirm a safe, non-damaging grasp. Industry inspection systems explicitly engineer their de-nest/inspect/re-nest handling to prevent glass-to-glass contact, underscoring the difficulty.
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.