Abstract
A pneumatic robot gripper capable of sorting eggplants according to their firmness has been developed and tested. The gripper has three fingers and one suction cup. Each finger has an inertial sensor attached to it. One of the fingers adapts to and copies the shapes of eggplants when the jamming of its internal granular material changes from soft to hard. The other fingers adapt to the shape of the eggplant with the use of extra degrees of freedom. Specific software acquires and processes the information obtained with the inertial sensors and generates 16 independent variables extracted from the signals. A total of 234 eggplants were selected and tested on the same day with the robot gripper, during the pick-and-place operation, and with a destructive firmness tester. The non-destructive parameters extracted from the gripper finger accelerometers were used to build and validate a partial least square model, with a calibration regression coefficient of r = 0.87 and a high prediction performance (r = 0.90). Furthermore, from the results of the paper, it has been seen that the procedure can be simplified by using only two non-destructive impacts and one uniaxial accelerometer to assess eggplant firmness. The non-destructive assessment of firmness while grasping agricultural products in pick-and-place operations could be implemented in many prehensile pneumatic robot grippers. This technique could mean an important advance in the hygienic postharvest handling of fruits and vegetables.
