Autonomous Excavator Control via 3D Pile Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current excavator operations rely heavily on manual operation, limiting the number of qualified drivers and resulting in idle equipment and reduced economic benefits due to the need for specialized operators.
Innovation Solution
A method and apparatus that utilize a camera to acquire a two-dimensional image of a material pile, generate a three-dimensional model, determine a target excavating point and trajectory, and control the excavator autonomously to excavate materials, reducing labor costs and improving economic efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual operation is used, then the excavator can be operated with simple control, but the number of qualified drivers is limited resulting in idle equipment
Solution Approach 1:
The excavator performs excavation operations autonomously without human intervention. The system captures images, generates 3D models, plans trajectories, and controls excavation automatically, allowing the machine to serve itself and eliminating the need for specialized operators.
Solution Approach 2:
The manual mechanical operation system is replaced with an automated system using cameras, image processing, 3D modeling, and computer control. The mechanical control by human operators is substituted with electronic sensors, algorithms, and automated actuators.
2Productivity
If automated control is implemented, then the excavator can operate autonomously improving utilization rate, but the system complexity increases requiring advanced imaging and processing
Solution Approach 1:
The control system integrates multiple functions into a unified automated platform: image capture, 3D reconstruction, trajectory planning, and excavation control. This multi-functional system improves productivity while managing complexity through integration rather than separate systems.
Solution Approach 2:
The system introduces intermediate processing stages between sensing and actuation: image processing generates 3D models, which then generate trajectory plans, which finally control the excavation. These intermediary steps break down complexity into manageable sequential processes.
3Manufacturing precision
If 3D modeling and trajectory planning are used, then precise excavation control is achieved, but the processing time and computational complexity increase
Solution Approach 1:
The system performs preliminary actions by capturing images and generating 3D models before excavation begins. The trajectory is planned in advance based on the 3D model, allowing precise control during actual excavation without real-time computational delays.
Solution Approach 2:
The excavation process is segmented into distinct phases: image capture, 3D model generation, trajectory planning, and execution. Each phase processes specific data independently, reducing overall computational complexity and time while maintaining precision through systematic breakdown of the task.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The autonomous excavation system allows for efficient operation of excavators, reducing labor costs and enhancing economic benefits by enabling precise control and optimizing excavation processes.
Implementation Method 1
performing image matching on the binocular image to obtain a parallax image of the binocular image; generating a depth image of the material pile based on the parallax image
Data Source
AI summary
Embodiments of the present disclosure relate to a method and apparatus for controlling an excavator to excavate. The method includes: acquiring a two-dimensional image of a material pile; generating a three-dimensional model of the material pile based on the two-dimensional image; analyzing the three-dimensional model to determine a target excavating point and a target excavating trajectory of the material pile; and controlling an excavator to excavate a material at the target excavating point along the target excavating trajectory.