Zoned Box Gripper Control for Picking in Walled Containers
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 caused by visual edges from textures and advertising, leading to slipping or incorrect picking.
Innovation Solution
A zoned gripper system with a control system that divides the gripper's grip area into zones based on minimum box size, using a visual sensor to locate candidate boxes, determine overlap with neighboring boxes, and compute a grasp pose that avoids container walls, ensuring sufficient suction force and precise lifting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Difficulty of detecting and measuring
If computer-vision-based systems are used to locate boxes, then the system can identify box positions, but visual edges from textures and advertising cause misjudgment of size and position
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 specific regions that correspond to the actual box boundaries, rather than relying solely on visual edge detection. The zoned structure enables precise control over which areas engage with the box, compensating for visual measurement errors.
Solution Approach 2:
Different zones of the gripper can be independently controlled to provide localized suction forces. This allows the system to adapt the grip pattern to the actual physical boundaries of the box, rather than using a uniform grip approach. The local quality control enables precise adjustment of suction application points based on real-time feedback about box location and size.
2Force
If a uniform gripper activates all zones for picking, then sufficient suction force is achieved, but boxes of varying sizes may slip or multiple boxes may be picked
Solution Approach 1:
The gripper transitions from a static, uniform activation pattern to a dynamic, selective activation pattern. The control system adjusts which zones are activated based on the detected box characteristics and desired grasp pose. This dynamic adaptation allows the system to optimize suction force distribution for each specific picking scenario, ensuring reliable grip on boxes of varying sizes without accidentally engaging multiple boxes.
Solution Approach 2:
The system changes the activation state parameter of different gripper zones based on box detection results. Instead of maintaining a constant full-activation state, the control system dynamically adjusts which zones are active, modifying the effective suction force distribution to match the actual box boundaries and size, thereby improving picking reliability.
3Measurement precision
If the gripper picks boxes from known pre-programmed locations on structured pallets, then picking accuracy is maintained, but any deviation from known structure causes system failure
Solution Approach 1:
The system performs preliminary visual detection and box localization before the picking action. By using vision systems to identify actual box positions and dimensions in real-time, the system adapts its gripper activation pattern accordingly, rather than relying on pre-programmed fixed locations. This preliminary detection enables the system to handle varied box arrangements while maintaining picking accuracy.
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 containers with walls, avoiding collisions and minimizing disturbance to other contents, by activating only non-overlapping zones for lifting and planning a motion path that avoids container features.
Implementation Method 1
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.