Assembly Guidance Using Neural Network Part Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face low assembly efficiency when assembling the JIMU robot due to the large number of similar components, making it difficult to quickly identify the required parts in the 3D demonstration animation.
Innovation Solution
A method utilizing pre-trained neural networks to identify and mark the required parts in real-time photos, displayed within a 3D demonstration animation, allowing users to easily locate the necessary components for the current assembly step.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a 3D demonstration animation with model photos of components is used to assist assembly, then the assembly guidance is provided, but the user cannot find the required components quickly due to the large number of similar components
Solution Approach 1:
The system uses image recognition technology to automatically identify and locate the required components in the user's physical environment by capturing images with a camera. The neural network model performs self-service by autonomously matching the 3D model components with real-world components, eliminating the need for users to manually search through numerous similar parts.
Solution Approach 2:
The patent replaces the manual mechanical search process with an automated image recognition and neural network-based identification system. Instead of users visually scanning and identifying components manually, the system uses computer vision technology to automatically detect, recognize, and locate the required components in real-time.
2Loss of information
If model photos of components are displayed in the 3D demonstration animation, then assembly instructions are provided, but users spend a long time to identify and determine whether the component is needed
Solution Approach 1:
The system implements real-time feedback by continuously monitoring the assembly process through camera input, automatically identifying the current assembly step, and providing immediate guidance on which component is needed next. The neural network model provides feedback by comparing the current state with the assembly instructions and highlighting the specific component required.
Solution Approach 2:
The system performs preliminary identification and verification of components before the user needs to select them. The neural network model pre-processes the image data to identify potential components and determines their relevance to the current assembly step in advance, so that when the user needs to select a component, the system has already narrowed down the options.
3Adaptability or versatility
If there are many types and numbers of components in the robot, then the robot functionality is enhanced, but the assembly efficiency becomes extremely low
Solution Approach 1:
The system automatically manages the complexity of numerous components through self-service image recognition and identification. Instead of requiring users to track and manage many different component types manually, the system autonomously identifies each component, determines its required location, and guides the user through the assembly process, thereby maintaining high assembly efficiency despite the large number of component varieties.
Data Source
AI summary
The present disclosure is provides a method, an apparatus and a terminal device for constructing parts together. The method includes: determining an assembly progress of an object constructed of parts; determining a currently required part according to the assembly progress; identifying, in a part photo of the object, the currently required part using a pre-trained first neural network model and marking the one or more identified currently required parts in the part photo; and displaying, via a display, a 3D demonstration animation with the marked part photo as a background image. The method is based on the existing 3D demonstration animation, which identifies the currently required part in the captured part photo and marks the identified currently required part in the part photo, and then displays the marked part photo as the background image of the 3D demonstration animation, thereby adding a prompt for the real part.