Automatic gripper fingertip design to reduce leftover in random bin picking applications

A computer program product implemented on non-transitory computer readable media, said computer program product being configured to cause a computing device to perform steps comprising:

• providing a gripper model including parameters defining size or shape features of gripper fingertips;
• providing an object model for an object to be grasped, a grasp database defining stable grasps on the object, and size dimensions of a bin;
• selecting values of the parameters to define a specified fingertip design;
• evaluating a bin picking performance of the specified fingertip design, including repeatedly simulating part-by-part bin picking for a quantity of simulated bins, where each part-by-part bin picking includes defining a quantity of the objects in random poses in the bin, repeatedly simulating picking an object with a gripper having the specified fingertip design using the grasps in the grasp database and a collision detection algorithm, and determining a number of leftover objects when no pickable objects remain in the bin, where the bin picking performance is based on the number of leftover objects for all of the simulated bins;
• recursively selecting new values of the parameters to define a new specified fingertip design and evaluating the bin picking performance of the new specified fingertip design;
• and
• selecting an optimized fingertip design as the one of the specified fingertip designs having a best bin picking performance.