Online ML Control for Earth Moving Vehicle Soil Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous control systems for earth moving vehicles face challenges in adapting to changing soil conditions and varying models of earth moving vehicles, due to complex control surface layouts and actuation methods, which hinders efficient autonomous operation.
Innovation Solution
An autonomous earth moving system that integrates sensors and machine learning models to record and process data for generating digital representations of the work site, selecting optimal tool paths, and controlling control surfaces, allowing the vehicle to adapt to soil parameters and conditions in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If traditional control systems are used for earth moving vehicles, then manual operation is straightforward, but autonomous operation cannot be achieved and labor costs are high
Solution Approach 1:
The control system enables the earth moving vehicle to autonomously perform earth moving operations without continuous human intervention. The system self-adjusts control parameters based on sensor feedback and pre-stored control rules, allowing the vehicle to service itself during operation.
Solution Approach 2:
The patent replaces manual mechanical control with an automated control system that uses sensors, processors, and actuators. The control system substitutes human operators by implementing automated decision-making algorithms and control rules that process sensor data and generate control signals for vehicle operations.
2Adaptability or versatility
If autonomous control is implemented, then labor costs are reduced, but the system cannot adapt to changing soil conditions and vehicle models
Solution Approach 1:
The control system dynamically adjusts control parameters based on real-time sensor feedback and changing operating conditions. The system modifies control rules and parameters adaptively to respond to varying soil conditions, vehicle states, and environmental factors, making the control behavior flexible rather than static.
Solution Approach 2:
The patent changes control parameters such as tool path coordinates, actuation forces, and operational speeds based on sensor measurements of soil conditions and vehicle state. The system stores multiple sets of control parameters for different conditions and selects appropriate parameters dynamically to optimize performance across varying environments.
3Productivity
If manual operation is used, then operation costs are high, but the control system is simple
Solution Approach 1:
The control system enables continuous autonomous operation of the earth moving vehicle without interruption by manual intervention. The vehicle continuously performs earth moving tasks by processing sensor data and executing control actions in real-time, maximizing productivity and utilization of the equipment.
4Adaptability or versatility
If complex control surfaces are used, then vehicle functionality is enhanced, but autonomous control becomes difficult to implement
Solution Approach 1:
The control system segments the complex control task into multiple independent control modules, each responsible for specific control surfaces or functions. The system divides control of different vehicle components (excavator arm, bucket, conveyor, etc.) into separate controllable elements that can be managed independently and coordinated through integrated control logic.
Data Source
AI summary
An autonomous earth moving system can determine a desired state for a portion of the EMV including at least one control surface. Then the EMV selects a set of control signals for moving the portion of the EMV from the current state to the desired state using a machine learning model trained to generate control signals for moving the portion of the EMV to the desired state based on the current state. After the EMV executes the selected set of control signals, the system measures an updated state of the portion of the EMV. In some cases, this updated state of the EMV is used to iteratively update the machine learning model using an online learning process.