Compliant handling of soft/deformable bars and frozen items for transfer and loading
Products such as RXBAR protein bars, cereal/granola bars, Rice Krispies Treats, and Eggo/MorningStar frozen items are soft, tacky, or temperature-sensitive deformable objects that must be picked, oriented, and loaded into wrappers, cartons, or trays. Their geometry changes with temperature and formulation (a warm bar deforms and sticks; a frozen waffle is rigid but chip-prone at the edges), so handling requires compliance and grip-force control to avoid denting, smearing, or cracking the product while keeping orientation for downstream wrapping. The task sits between forming/cutting/freezing and secondary packaging, runs at high volume, and is a recurring labor and quality point on bar and frozen lines. It is difficult for a robot because the same gripper must adapt to compliant, variable, sometimes sticky surfaces and confirm a clean, undamaged hold — feedback vision struggles to provide. No Kellanova-specific dexterous robotics signal was found, so demand here is inferred from the product physics, not stated need. 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 reconstructionProducts such as RXBAR protein bars, cereal/granola bars, Rice Krispies Treats, and Eggo/MorningStar frozen items are soft, tacky, or temperature-sensitive deformable objects that must be picked, oriented, and loaded into wrappers, cartons, or trays. Their geometry changes with temperature and formulation (a warm bar deforms and sticks; a frozen waffle is rigid but chip-prone at the edges), so handling requires compliance and grip-force control to avoid denting, smearing, or cracking the product while keeping orientation for downstream wrapping. The task sits between forming/cutting/freezing and secondary packaging, runs at high volume, and is a recurring labor and quality point on bar and frozen lines. It is difficult for a robot because the same gripper must adapt to compliant, variable, sometimes sticky surfaces and confirm a clean, undamaged hold — feedback vision struggles to provide. No Kellanova-specific dexterous robotics signal was found, so demand here is inferred from the product physics, not stated need.
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.