Work Implement Position Estimation Using Imaging Device

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The existing configuration for determining the posture of a work implement in hydraulic excavators requires attaching multiple angle sensors, increasing the number of components and complexity.

Innovation Solution

A system comprising a work machine, an imaging device, and a computer with a trained position estimation model that captures images of the work implement and uses neural networks to determine its position, eliminating the need for additional sensors.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If angle sensors are attached to the boom, dipper stick, and bucket to determine work implement posture, then the position measurement accuracy is improved, but the device complexity increases due to the increased number of components

Engineering Contradiction:
Improveposition measurement accuracyVSAvoiddevice complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces the mechanical sensor-based measurement system with a vision-based system. Instead of using angle sensors attached to mechanical components (boom, dipper stick, bucket), the invention uses an imaging device to capture images and a computer to calculate positions based on image processing and geometric relationships. This substitution eliminates the need for multiple physical sensors while maintaining position determination capability.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates a visual copy (image) of the work implement and its components. By capturing images of the boom, dipper stick, and bucket through an imaging device, the system creates a digital representation that can be processed to determine positions. This copying approach replaces direct physical measurement with optical measurement and computational analysis.

Inventive Principle:
Principle #26Copying

2Measurement precision

If multiple angle sensors are attached to determine work implement posture, then the position determination capability is improved, but the reliability decreases due to more potential failure points

Engineering Contradiction:
Improveposition determination capabilityVSAvoidreliability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent replaces the mechanical sensor system with a vision-based system, thereby eliminating the reliability issues associated with multiple mechanical sensors. The imaging device and computer-based calculation system have fewer moving parts and potential failure points compared to multiple angle sensors attached to mechanical components.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The imaging device serves multiple functions: it captures images of the boom, dipper stick, and bucket, and these images are used to determine the positions of all three components simultaneously. This multi-functional approach replaces multiple dedicated sensors with a single imaging device that provides comprehensive position information.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS11814817B2System including work machine, computer implemented method, method for producing trained position estimation model, and training data
Publication Date: 2023.11.14 KOMATSU LTD
  • US11814817B2 patent drawing
  • US11814817B2 patent drawing
  • US11814817B2 patent drawing

AI summary

A work implement's position is determined. Provided is a system including a work machine, the system comprising: a work machine body; a work implement attached to the work machine body; an imaging device that captures an image of the work implement; and a computer. The computer includes a trained position estimation model. The computer is programmed to obtain the image of the work implement captured by the imaging device and use the trained position estimation model to obtain a position of the work implement estimated from the captured image.