Zoned Vacuum Gripper for Wall-Aware Box Picking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current robotic systems fail to accurately pick and manipulate boxes of varying sizes and orientations from containers with walls due to misjudgment of size and position, often causing slippage or incorrect picking, especially when boxes have visual edges from advertising, logos, or textures that confuse computer-vision-based systems.
Innovation Solution
A zoned gripper system with a control system that divides the gripper's suction cup area into zones based on minimum box size, uses visual sensors to identify candidate boxes, determines grasp poses that avoid container walls, and activates zones to lift boxes without overlapping neighboring boxes, ensuring sufficient suction force and avoiding container features during removal.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Difficulty of detecting and measuring
If computer-vision-based systems are used to identify boxes, then visual detection capability is improved, but measurement precision deteriorates due to visual edges from advertising, logos, or textures confusing the system
Solution Approach 1:
The gripper is divided into multiple independently controllable zones with vacuum suction cups, allowing selective activation of specific zones based on the detected box position and size. This segmentation enables precise grasping of individual boxes even when visual edges are present, as the control system can activate only the zones corresponding to the target box's location.
Solution Approach 2:
Different zones of the gripper can be independently controlled to provide localized grasping force. The control system determines which specific zones to activate based on the box's position, size, and orientation, applying suction force only where needed rather than uniformly across the entire gripper surface.
2Device complexity
If a uniform gripper design is used, then device complexity is reduced, but adaptability deteriorates when handling boxes of varying sizes and orientations
Solution Approach 1:
The gripper comprises multiple zones with vacuum suction cups that can be independently controlled. This segmentation allows the same gripper structure to adapt to boxes of different sizes and orientations by selectively activating appropriate zones, maintaining structural simplicity while achieving high versatility.
Solution Approach 2:
The gripper transitions from a static, uniform design to a dynamic, selectively controllable system. The control system can activate or deactivate specific zones based on real-time detection of box characteristics, enabling the same physical structure to adapt to varying box sizes, shapes, and orientations.
3Reliability
If the gripper activates all zones for maximum coverage, then grasp reliability is improved, but harmful factors increase due to overlapping with neighboring boxes causing slippage or incorrect picking
Solution Approach 1:
By dividing the gripper into independently controllable zones, the system can activate only the zones corresponding to the target box's location and size. This prevents activation of zones that would overlap with neighboring boxes, eliminating the harmful effects of slippage and incorrect picking while maintaining sufficient grasp reliability through selective zone activation.
Solution Approach 2:
The control system applies suction force locally to only those zones that correspond to the target box, rather than activating all zones uniformly. This localized activation ensures reliable grasping of the intended box while avoiding interference with adjacent boxes, preventing slippage and incorrect picking.
4Ease of operation
If conventional picking methods are used, then ease of operation is maintained, but productivity deteriorates due to system failure requiring manual intervention
Solution Approach 1:
The system uses visual sensors to detect box positions, sizes, and orientations, providing feedback to the control system. Based on this feedback, the control system selectively activates appropriate gripper zones to ensure successful grasping. This closed-loop feedback mechanism eliminates system failures and manual interventions, maintaining operational simplicity while significantly improving picking efficiency.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables reliable picking and movement of individual boxes of varying sizes and orientations from mixed-SKU containers with walls, reducing collisions and disturbances, and ensuring accurate grasping and removal while minimizing container interference.
Implementation Method 1
The robot includes a gripper with a plurality of vacuum suction cups
Data Source
Figure 1
Figure 2A
Figure 2B~2D
AI summary
A method of manipulating boxes (22) includes receiving a minimum box size for a plurality of boxes varying in size located in a walled container (30). The method also includes dividing a grip area of a gripper (200) into a plurality of zones (Z). The method further includes locating a set of candidate boxes (24, 24T) based on an image from a visual sensor (120). For each zone, the method additionally includes, determining an overlap of a respective zone with one or more neighboring boxes (26) to the set of candidate boxes. The method also includes determining a grasp pose (PG) for a target candidate box (24T) that avoids one or more walls (30w) of the walled container. The method further includes executing the grasp pose to lift the target candidate box by the gripper where the gripper activates each zone of the plurality of zones that does not overlap a respective neighboring box (26) to the target candidate box.