Robot Tire Picking With Neural Vision for Unknown Bulk Arrangements

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing tire handling systems struggle with unpredictable and heterogeneous bulk tire arrangements, requiring specific hardware setups and CAD data for precise object detection, which fail in environments with significant variations or unknown tire configurations.

Innovation Solution

A tire picking system utilizing a robot with a gripper and unsupervised learning to reconstruct 3D point clouds from scattered views, employing a neural network for tire parameter determination and a gripper with pivotable fingers to engage sidewalls for stable picking in unknown arrangements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional vision systems with CAD data and fixed hardware setups are used for tire detection, then measurement precision is improved for known configurations, but adaptability deteriorates when facing unknown or heterogeneous tire arrangements

Engineering Contradiction:

Improvetire detection precisionVSAvoidadaptability to unknown arrangements

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The system performs self-calibration by automatically adapting to the actual tire arrangement in the container without requiring pre-programmed CAD data or fixed hardware configurations. The vision system learns the spatial relationships and tire characteristics directly from the environment, enabling it to handle heterogeneous bulk tire arrangements autonomously

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system dynamically adjusts detection parameters and gripper positioning based on real-time vision data rather than relying on fixed parameters. This allows the system to adapt to varying tire sizes, positions, and arrangements by changing operational parameters on-the-fly

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If specialized hardware facilities and fixed environment references are used for tire picking, then measurement precision is improved, but device complexity increases

Engineering Contradiction:

Improveobject detection precisionVSAvoidhardware setup complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The vision system serves multiple functions: it detects tire positions, determines tire orientations, guides gripper positioning, and adapts to different tire types all through a single flexible hardware setup, eliminating the need for multiple specialized sensors and fixed references

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system replaces complex mechanical positioning and fixed hardware facilities with a flexible vision-based guidance system that uses software algorithms to achieve precise tire detection and gripper control without requiring specialized mechanical infrastructure

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If model matching with CAD data is used for tire detection, then measurement precision is improved for identical tires, but ease of operation deteriorates when dealing with heterogeneous tire bulk

Engineering Contradiction:

Improvetire parameter detection precisionVSAvoidoperation simplicity

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The system automatically adapts to different tire types and arrangements without requiring manual intervention to load CAD data or reconfigure detection parameters. It self-calibrates by learning from the actual tire bulk configuration, making operation simple despite handling heterogeneous tires

Inventive Principle:

Principle #25Self-service

4Productivity

If fixed hardware setups and pre-programmed references are used for automated tire picking, then productivity is improved for known configurations, but adaptability deteriorates for unexpected environments

Engineering Contradiction:

Improveautomated picking speedVSAvoidadaptability to unexpected environments

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The system maintains high productivity by automatically adapting to unexpected tire arrangements through real-time vision processing and dynamic parameter adjustment, eliminating the need for manual reprogramming while handling heterogeneous bulk tires

Inventive Principle:

Principle #25Self-service

Data Source

PatentEP4267349B1System and process for picking tires in an unknown arrangement

Publication Date: 2026.04.15 MICHELIN & CO (CIE GEN DES ESTAB MICHELIN)

Figure 1~2
Figure 3~4
Figure 5~6

AI summary

The invention is directed to a tire picking system (100) that performs a process for picking one or more tires stored in an unknown arrangement and for which a target location must be realized. The invention is also directed to a gripper (108) forming part of such a tire picking system (100). The invention is also directed to a robot (102) including a gripping device (104) supported by a pivotable elongated arm (106), the gripping device extending from the elongated arm to a free end (104a) where the gripper of the invention is disposed. The disclosed inventions involve an image processing module that applies data representative of the physical environment around the robot (102) to a deployed neural network in order to determine, using the deployed neural network, one or more parameters of a target tire (P*); such that the robot is set in motion based on the determined parameters of the target tire, so that the gripper can pick a target tire (P*) selected by the system (100) from among the stored tires along an inner boundary (FI) of a sidewall (F) of the selected target tire (P*).