Manipulation and port-handling of flexible, fluid-filled cell-culture and apheresis bags
Throughout the process, operators handle floppy single-use bags — patient apheresis collection bags, media/feed bags, and culture bags — that are fluid-filled, deformable, fragile at weld seams, and (for the cell-bearing bags) irreplaceable autologous material. Tasks include loading and positioning bags into instruments and manifolds, presenting and mating their ports/tubing for connection, gently resuspending or rocking cells, and removing/sealing emptied bags. The objects have no fixed geometry: fill level, slosh, and membrane tension change as fluid moves, and grip must adapt continuously. This sits at the heart of every expansion and harvest step and is a major manual-touch bottleneck the industry is trying to close. It is hard for a robot because a rigid or force-blind grasp can puncture a bag or stress a seam, and a fumble cannot be retried on a one-of-one patient product. 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 reconstructionThroughout the process, operators handle floppy single-use bags — patient apheresis collection bags, media/feed bags, and culture bags — that are fluid-filled, deformable, fragile at weld seams, and (for the cell-bearing bags) irreplaceable autologous material. Tasks include loading and positioning bags into instruments and manifolds, presenting and mating their ports/tubing for connection, gently resuspending or rocking cells, and removing/sealing emptied bags. The objects have no fixed geometry: fill level, slosh, and membrane tension change as fluid moves, and grip must adapt continuously. This sits at the heart of every expansion and harvest step and is a major manual-touch bottleneck the industry is trying to close. It is hard for a robot because a rigid or force-blind grasp can puncture a bag or stress a seam, and a fumble cannot be retried on a one-of-one patient product.
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.