Vision-Based Container Angle Sensing for Earth-Mover Volume Estimation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems for measuring the efficiency of earth-moving operations, such as excavators, face challenges in accurately estimating the volume of materials in containers without physical contact, which can disrupt the process and lead to inefficiencies.

Innovation Solution

A mobile work machine equipped with a stereo camera and an angle determination system that captures images of the container, determines its angle, and calculates the volume of materials using 3D point clouds and mathematical models, allowing for non-contact, accurate volume estimation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If physical contact methods are used to measure container contents (e.g., positioning bucket to weigh contents), then measurement accuracy is improved, but operational efficiency deteriorates due to additional steps required

Engineering Contradiction:
Improvevolume measurement accuracyVSAvoidearth-moving efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces mechanical/physical contact measurement systems with an optical vision-based system. The image sensor captures images of the container, and image processing algorithms calculate the volume of contents without requiring physical contact or special positioning of the container, thus maintaining measurement accuracy while eliminating operational disruptions

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

Solution Approach 2:

The patent introduces an image sensor and image processing system as an intermediary between the container and the measurement function. This intermediary enables non-contact volume estimation by capturing visual data and processing it through algorithms that calculate content volume based on image analysis

Inventive Principle:
Principle #24Intermediary (Mediator)

2Productivity

If vision sensors are used to estimate container volume without contact, then operational efficiency is improved, but measurement accuracy deteriorates compared to physical contact methods

Engineering Contradiction:
Improveearth-moving efficiencyVSAvoidvolume estimation accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent transitions from 2D image data to 3D volume estimation by processing image sequences and calculating spatial relationships. The system determines container angle, calculates content volume based on multiple image perspectives, and uses geometric relationships to derive accurate 3D measurements from 2D visual data

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent implements feedback mechanisms where the determined container angle and volume estimates are used to continuously refine measurements. The system processes image sequences over time, compares measurements, and adjusts calculations to improve accuracy while maintaining continuous non-contact monitoring

Inventive Principle:
Principle #23Feedback

3Measurement precision

If additional sensors are added to improve measurement capabilities, then measurement precision is improved, but device complexity and cost increase

Engineering Contradiction:
Improvevolume measurement capabilityVSAvoidsensor system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent makes the image sensor multi-functional by using it for both container angle determination and volume estimation. Instead of requiring separate sensors for these functions, the system processes the same image data to extract multiple measurement parameters, reducing overall system complexity while maintaining measurement precision

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

Solution Approach 2:

The patent combines angle determination and volume measurement functions into a single integrated system. The image sensor, processing unit, and algorithms work together to simultaneously determine container orientation and calculate content volume, eliminating the need for separate sensor systems

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS10689830B2Container angle sensing using vision sensor for feedback loop control
Publication Date: 2020.06.23 DEERE & CO
  • US10689830B2 patent drawing
  • US10689830B2 patent drawing
  • US10689830B2 patent drawing

AI summary

A mobile work machine includes a frame and a ground engaging element movably supported by the frame and driven by an engine to drive movement of the mobile work machine. The mobile work machine also includes a container movably supported by the frame and an actuator configured to controllably drive movement of the container relative to the frame. The work machine also includes a control system configured to generate an actuator control signal, indicative of a commanded movement of the actuator, and provide the actuator control signal to the actuator to control the actuator to perform the commanded movement and an image sensor coupled to the mobile work machine, the image sensor being configured to capture an image of the container. The work machine also includes an angle determination system, communicatively coupled to the control system, configured to determine an angle of the container relative to the image sensor, based on the image of the container.