Robotic Pick Filtering and Sorting for Overlapping Conveyor Objects
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robotic gripper systems face challenges in precisely identifying and handling products that are touching or overlapping on a conveyor belt, leading to slower picks, incorrect picks, or potential damage, and struggle with variability in product size, shape, and weight, requiring adaptable gripping mechanisms.
Innovation Solution
A method combining machine learning and rules-based algorithms for filtering and sorting pick candidates, using object tracking logic to apply filtering rules based on motion, type, occlusion, and proximity, and sorting rules based on pose and orientation, allowing efficient and accurate selection of pick targets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional sensor and controller systems are used to identify products on a conveyor belt, then the system can detect objects, but it struggles with products that are touching or overlapping, leading to slower picks and incorrect picks
Solution Approach 1:
The vision system segments overlapping products by detecting edges and contours, separating touching objects into distinct identifiable units. This allows the system to accurately identify individual products even when they are in contact, resolving the measurement precision issue without sacrificing speed.
Solution Approach 2:
The system performs preliminary sorting and filtering of pick candidates using rules-based logic before the actual picking operation. By pre-identifying and ranking suitable targets, the system reduces computation time during execution, maintaining high productivity while improving identification accuracy.
2Reliability
If the gripper applies strong force to secure products, then products are less likely to be dropped, but products may be damaged due to excessive gripping force
Solution Approach 1:
The gripping force parameter is dynamically adjusted based on product characteristics detected by the vision system and defined in the product database. Different products receive optimized grip forces from the soft gripper, ensuring secure holding without excessive force that could cause damage.
Solution Approach 2:
The system uses a soft gripper with flexible material that can conform to different product shapes and sizes. This flexibility allows the gripper to distribute force evenly across the product surface, maintaining secure grip while minimizing localized stress that could cause damage.
3Measurement precision
If the system uses complex filtering and sorting logic to handle variable product sizes and shapes, then pick accuracy improves, but processing time increases
Solution Approach 1:
The filtering and sorting process is segmented into multiple stages: initial filtering based on basic criteria, then progressive refinement through sorting rules. This multi-stage approach processes complex product variations efficiently by handling simple cases quickly and reserving detailed analysis for ambiguous situations.
Solution Approach 2:
The system uses a product database that stores pre-defined characteristics and handling parameters for different product types. Instead of analyzing every product from scratch, the system copies relevant parameters from the database match, significantly reducing processing time while maintaining accurate selection.
4Productivity
If the robotic arm moves quickly to maintain high throughput, then productivity increases, but tracking accuracy decreases making precise picking difficult
Solution Approach 1:
The vision system continuously tracks products on the conveyor belt and provides real-time feedback to the robotic arm controller. This closed-loop system adjusts for product position variations and conveyor speed fluctuations, maintaining tracking accuracy even at high speeds.
Solution Approach 2:
The system performs preliminary tracking and prediction of product positions before the robotic arm reaches the picking zone. By anticipating where products will be located based on conveyor speed and product motion, the system maintains accuracy without requiring slower operation speeds.
Data Source
AI summary
Exemplary embodiments provide a rules-based approach to identifying a next pick for a robotic gripper or series of robotic grippers in a robotic pick-and-place system. A filtering process eliminates occluded objects or those likely to cause collisions, and a sorting process prioritizes the remaining items to identify the best pick. The filtering and sorting process may be employed in conjunction with machine-learning-based object detection and/or tracking, but can provide a more efficient and faster procedure than a system relying solely on an ML approach. The rules-based approach can be applied to quickly select a suitable target that can be best approached by a gripper. This may improve the accuracy and/or throughput of the system. Moreover, the rules can be adjusted to achieve different effects, such as improved throughput on a given robotic arm, load balancing between different robotic arms, different priorities or different arms, etc.