Current robotic gripping technology is able to handle well-defined, rigid objects. However, grippers for harvesting, food processing, and packaging have to perform their tasks under demanding requirements, such as robustness to variability in product size, shape, and softness, and fast operation to reduce cycle times. State-of-the-art robotic technology does not address these challenges. This large variation demands different grasp types, with different force distributions and different grasp stiffness. We will approach these challenges using compliant mechanism based grippers which on the one hand allow integration of complex functionality such as underactuation, softness adaptability and joint locking, but on the other hand pose challenges such as limited load bearing capacity, off-axis stiffness and compactness due to a limited range of motion.
Program coherence: Active perception (P1) and the world model (P2) provide input to P4 in terms of size, geometry and material properties. Tactile sensing provided by the gripper (P4) will be input to active perception (P1) and world model (P2). Low level control will be embedded in the gripper device. High-level guidance of gripping and ma- nipulation will be provided by planning and control (P3). P3 provides the specific instances of gripping and manipulation capabilities in the use-case pro- jects P5, P6 and P7.
Research Team: UT-PE, TUD-IM, UT-RAM
User involvement: Marel, Demcon, Cerescon, Fes- to, Houdijk, BluePrint Automation, Protonic, Maxon Motor.