Robotic Storage Box Handling Using Stored Object Positions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robotic systems face challenges in accurately recognizing and gripping objects within storage boxes, leading to inefficiencies in unpacking and packing processes.
Innovation Solution
A control device and method that utilize first box information acquired during packing, combined with sensor data and object recognition, to generate precise control instructions for robotic devices to improve object recognition and gripping accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If object recognition is performed using only sensor data from the storage box, then the system remains simple, but the classification rate of correctly recognized objects decreases
Solution Approach 1:
The system performs preliminary action by acquiring packing information about objects during the packing process and storing it in a database. This pre-acquired information includes object positions, orientations, and identification data. When unpacking occurs, this pre-stored information is retrieved and combined with sensor data to significantly improve object recognition accuracy without requiring complex real-time analysis during unpacking.
2Manufacturing precision
If traditional object recognition methods are used without packing information, then the system is simpler to operate, but the gripping accuracy of robotic devices decreases
Solution Approach 1:
The system implements feedback by utilizing packing information that was recorded during the packing process. This information serves as a reference feedback loop that provides expected object locations, orientations, and identification data. The robotic device compares this feedback information with actual sensor data during unpacking, enabling highly accurate gripping while maintaining ease of operation through automated decision-making.
3Productivity
If manual intervention is used for object recognition and gripping, then recognition accuracy can be maintained, but productivity of the warehouse system decreases
Solution Approach 1:
The system applies self-service by enabling the robotic device to autonomously perform object recognition and gripping tasks using a combination of sensor data and pre-stored packing information. The system serves itself by automatically retrieving relevant packing information from the database, comparing it with current sensor data, and making decisions about object identification and gripping without human intervention, thereby maintaining high productivity and accuracy simultaneously.
Data Source
AI summary
A control device includes a memory device storing, for each storage box of a plurality of storage boxes, respectively associated first box information indicating which multiple objects are arranged in the storage box and in which arrangement the multiple objects are in the storage box; and a processor configured to: receive identification data representing an identification of a storage box; determine the first box information associated with the storage box using the identification data; receive sensor data representing an image of the multiple objects arranged in the storage box; determine, via object recognition using the sensor data, second box information indicating which objects are arranged in the storage box; generate control instructions for controlling the robotic device to pick up at least one object of the multiple objects based on the first box information associated with the storage box and the second box information.