# US 2024/0198543 A1 · Automatic gripper fingertip design to reduce leftover in random bin picking applications > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2024/0198543 A1 - Document ID: US20240198543A1 - Status: Published application - Kind: A1 - Application number: 18/067,110 - Filed: 2022-12-16 - Published: 2024-06-20 - Earliest claimed: 2022-12-16 - Assignees: Fanuc Corporation - Applicants: Fanuc Corporation - Inventors: Yongxiang Fan; Tetsuaki Kato - Web page: https://patentgrep.com/patent/US20240198543A1 ## CPC - B25J 19/007: {Means or methods for designing or fabricating manipulators} - B25J 9/1612: {characterised by the hand, wrist, grip control} - B25J 9/163: {learning, adaptive, model based, rule based expert control} - B25J 9/1671: {characterised by simulation, either to verify existing program or to create and verify new program, CAD/CAM oriented, graphic oriented programming systems} - B25J: MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES ({manipulators specially adapted for use in surgery A61B34/70; manipulators used in cleaning hollow articles B08B9/04}; manipulators associated with rolling mills B21B39/20; manipulators associated with forging machines B21J13/10; {manipulators associated with picking-up and placing mechanisms B23P19/007}; means for holding wheels or parts thereof B60B30/00; {vehicles with ground-engaging propulsion means, e.g. walking members B62D57/02, B62D57/032; devices for picking-up and depositing articles or materials between conveyors B65G47/90, B65G47/91; manipulators with gripping or holding means for transferring packages B65H67/065}; cranes B66C; {manipulators used in the protection or supervision of pipe-line installations F17D5/00; walking equipment adapted for nuclear steam-generators F22B37/006}; manipulators specially adapted for, or associated with, nuclear reactors G21C; {apparatus used for handling wafers during manufacture or treatment of semiconductor H10P72/50}) ## Abstract An automated technique for robot gripper fingertip design. A workpiece design and a bin shape are provided as inputs, along with a parameterized gripper design. The gripper parameters define the lengths of segments of the fingertips, and the bend angle between fingertip segments. A fingertip shape, defined by selecting parameter values, is used in a simulated picking of parts from many different randomly defined piles of workpieces in the bin. Grasps for the simulated bin picking are pre-defined and provided as input. A score is assigned to the particular fingertip shape based on the average number of leftovers from the many simulated bin picking operations. A new fingertip shape is then defined by selecting new values for the parameters, and the simulations are repeated to assign a score for the new fingertip shape. This process is repeated to suitably sample the parameter range, and a best-performing fingertip shape is identified. ## Claims ### Claim 1 A method for robot gripper fingertip design, said method 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, on a computer having a processor and memory, 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. ### Claim 2 (depends on 1) The method according to claim 1 further comprising fabricating gripper fingers using the optimized fingertip design, and using the gripper fingers in a gripper on a robot performing actual bin picking of the object. ### Claim 3 (depends on 1) The method according to claim 1 wherein simulating picking an object includes selecting one object in the bin, mapping grasps from the grasp database to the one object, performing a collision detection computation for each of the mapped grasps, and assigning a pickability value to the one object based on the mapped grasps and the collision detection computation. ### Claim 4 (depends on 3) The method according to claim 3 further comprising repeatedly selecting another one object in the bin until all of the objects in the bin have a pickability value assigned. ### Claim 5 (depends on 4) The method according to claim 4 wherein, when all of the objects in the bin have a pickability value assigned, an object to pick is selected based on a user-defined rule. ### Claim 6 (depends on 5) The method according to claim 5 wherein the rule is to select the object to pick based on a greatest pickability value or a greatest clearance to other objects during grasping. ### Claim 7 (depends on 5) The method according to claim 5 wherein the rule is to select the object to pick based on a suitable pickability value and a greatest object height in the bin. ### Claim 8 (depends on 1) The method according to claim 1 wherein the quantity the objects in random poses in the bin is one. ### Claim 9 (depends on 1) The method according to claim 1 wherein the quantity the objects in random poses in the bin is greater than 10. ### Claim 10 (depends on 1) The method according to claim 1 wherein selecting an optimized fingertip design includes selecting the one of the specified fingertip designs having the fewest total leftover objects for all of the simulated bins, or selecting the one of the specified fingertip designs having the largest number of the simulated bins with zero leftover objects. ### Claim 11 (depends on 1) The method according to claim 1 wherein the parameters defining size or shape features of gripper fingertips include a length of a first segment of the gripper fingertips, a length of a second segment of the gripper fingertips, and a bend angle included between the first segment and the second segment. ### Claim 12 (depends on 1) The method according to claim 1 wherein repeatedly simulating part-by-part bin picking for a quantity of simulated bins includes a quantity of 500 or more simulated bins, and recursively selecting new values of the parameters to define a new specified fingertip design includes selecting new values of the parameters at least 50 times. ### Claim 13 A method for robot gripper fingertip design, said method 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; performing an optimization computation on the gripper fingertip design, on a computing device, including varying the parameters defining the gripper fingertips and for each set of parameter values performing multiple bin picking simulations until no collision-free object grasps remain, and determining an optimal fingertip design using the set of parameter values which resulted in a lowest number of leftovers from the multiple bin picking simulations. ### Claim 14 (depends on 13) The method according to claim 13 wherein performing an optimization computation on the gripper fingertip design includes: 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; and 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. ### Claim 15 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. ### Claim 16 (depends on 15) The computer program product according to claim 15 wherein simulating picking an object includes selecting one object in the bin, mapping grasps from the grasp database to the one object, performing a collision detection computation for each of the mapped grasps, and assigning a pickability value to the one object based on the mapped grasps and the collision detection computation, and repeatedly selecting another one object in the bin until all of the objects in the bin have a pickability value assigned. ### Claim 17 (depends on 16) The computer program product according to claim 16 wherein, when all of the objects in the bin have a pickability value assigned, an object to pick is selected based on a user-defined rule, and the rule is to select the object to pick based on a greatest pickability value, or a greatest clearance to other objects during grasping, or a greatest object height in the bin. ### Claim 18 (depends on 15) The computer program product according to claim 15 wherein selecting an optimized fingertip design includes selecting the one of the specified fingertip designs having the fewest total leftover objects for all of the simulated bins, or selecting the one of the specified fingertip designs having the largest number of the simulated bins with zero leftover objects. ### Claim 19 (depends on 15) The computer program product according to claim 15 wherein the parameters defining size or shape features of gripper fingertips include a length of a first segment of the gripper fingertips, a length of a second segment of the gripper fingertips, and a bend angle included between the first segment and the second segment. ### Claim 20 (depends on 15) The computer program product according to claim 15 wherein repeatedly simulating part-by-part bin picking for a quantity of simulated bins includes a quantity of 500 or more simulated bins, and recursively selecting new values of the parameters to define a new specified fingertip design includes selecting new values of the parameters at least 50 times.