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 resulting in slipping 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 grip area into zones based on the minimum box size, uses a visual sensor to locate candidate boxes, determines a grasp pose that avoids container walls, and activates zones to lift the target box without overlapping neighboring boxes, ensuring sufficient suction force and avoiding container features during removal.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If computer-vision-based systems are used to locate boxes, then the system can identify box positions, but the system misjudges size and position when boxes have visual edges from advertising, logos, or textures
Solution Approach 1:
The gripper is divided into multiple independently controllable zones that can be selectively activated. This segmentation allows the system to apply suction only to the target box while avoiding neighboring boxes, even when visual edges cause detection ambiguity. The zoned structure enables precise local control of the gripping force distribution.
Solution Approach 2:
Different zones of the gripper can be independently activated based on the detected box position and size. This local quality approach ensures that suction force is applied precisely where needed (on the target box) while leaving other areas inactive, thereby preventing misgrasping caused by visual edge confusion.
2Adaptability or versatility
If a uniform gripper activates all zones for picking, then the gripper can grasp large boxes, but the box slips or the gripper picks multiple boxes when boxes vary in size
Solution Approach 1:
The gripper transitions from a static uniform activation mode to a dynamic zoned activation mode. Based on real-time detection of box size and position, the control system dynamically determines which zones to activate, enabling the gripper to adapt its gripping pattern to match the specific dimensions of each target box, thereby preventing slippage and multi-box picking.
Solution Approach 2:
The system changes the activation parameters of different gripper zones based on the detected box characteristics. By adjusting which zones are active and their respective suction forces, the gripper optimizes its grasp for each specific box size, ensuring reliable grasping across varying dimensions.
3Ease of operation
If the gripper picks boxes from containers with walls, then the system can access enclosed boxes, but the gripper may collide with container walls or features
Solution Approach 1:
The system performs preliminary detection of box positions and container wall locations before executing the picking action. By pre-planning the gripper's approach path and activation zones based on this advance information, the system can navigate around container walls and features, preventing collisions while maintaining access to enclosed boxes.
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
The system reliably picks individual boxes of varying sizes and orientations from enclosed containers with walls, minimizing collisions and ensuring accurate grasping and movement, even in mixed-SKU environments with varying box sizes and orientations.
Implementation Method 1
The robot includes a gripper with a plurality of vacuum suction cups
Data Source
AI summary
A method of manipulating boxes includes receiving a minimum box size for a plurality of boxes varying in size located in a walled container. The method also includes dividing a grip area of a gripper into a plurality of zones. The method further includes locating a set of candidate boxes based on an image from a visual sensor. For each zone, the method additionally includes, determining an overlap of a respective zone with one or more neighboring boxes to the set of candidate boxes. The method also includes determining a grasp pose for a target candidate box that avoids one or more walls 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 to the target candidate box.