AGD Intelligence

Compliant handling and orientation of filled flexible wet-pet-food pouches

Mars Petcare produces large volumes of wet food in flexible retort pouches. Between filling/sealing and secondary packaging, individual filled pouches—floppy, fluid-filled, and non-rigid—must be grasped, oriented, and presented for cartoning or display-ready packing. The pouch changes shape as it is lifted, fluid shifts inside it, and the seal area must not be stressed or punctured. This task sits at the wet-food line's downstream end. It is hard for a robot because the object has no fixed geometry: a rigid pinch grasp can slosh contents, distort the pouch, or compromise a seal, and the contact point shifts as the pouch deforms in-hand. Specific Mars throughput figures for this step are not public; it is included as a genuinely deformable-handling task distinct from the bulk case-packing it feeds into. Note: the surrounding tote/case movement is throughput automation and out of AGD scope—only the deformable single-pouch manipulation qualifies. 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.

Readiness
build now
Demand
weak
Source
researched
Failure tol.
medium
Tactile value
medium
i

What the task is

RESEARCHED · our reconstruction

Mars Petcare produces large volumes of wet food in flexible retort pouches. Between filling/sealing and secondary packaging, individual filled pouches—floppy, fluid-filled, and non-rigid—must be grasped, oriented, and presented for cartoning or display-ready packing. The pouch changes shape as it is lifted, fluid shifts inside it, and the seal area must not be stressed or punctured. This task sits at the wet-food line's downstream end. It is hard for a robot because the object has no fixed geometry: a rigid pinch grasp can slosh contents, distort the pouch, or compromise a seal, and the contact point shifts as the pouch deforms in-hand. Specific Mars throughput figures for this step are not public; it is included as a genuinely deformable-handling task distinct from the bulk case-packing it feeds into. Note: the surrounding tote/case movement is throughput automation and out of AGD scope—only the deformable single-pouch manipulation qualifies.

To confirm with the customer

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.