Online Control-Surface Calibration for Autonomous Earthmoving Vehicles
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 to record vehicle and environmental data, uses machine learning models to determine optimal tool paths and control signals, and updates models based on real-time performance, enabling the vehicle to adapt to soil parameters and conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional control systems are used for earth moving vehicles, then manual operation is required which ensures basic adaptability to changing conditions, but operational cost increases and productivity decreases due to the need for continuous human intervention
Solution Approach 1:
The earth moving vehicle performs self-calibration by automatically determining calibration data for its control surfaces without external intervention. The system executes calibration routines, measures actual responses using sensors, and updates its own control models, enabling autonomous adaptation to changing soil conditions and vehicle states
Solution Approach 2:
The system implements continuous feedback loops where sensors monitor the actual response of control surfaces to control signals, compare them with predicted responses from calibration data, and automatically update calibration models. This closed-loop feedback enables real-time adaptation to changing work site conditions
2Adaptability or versatility
If calibration data is determined for each control surface to improve control precision, then adaptability to changing conditions improves, but device complexity increases due to multiple control surfaces with different actuation methods
Solution Approach 1:
The system uses a unified calibration approach that determines calibration data for multiple control surfaces with different actuation methods (hydraulic, electronic, pneumatic) through a single integrated process. The calibration framework is designed to handle various actuation types universally, reducing the complexity of managing separate calibration systems for each control surface type
Solution Approach 2:
The system dynamically adjusts calibration parameters based on changing soil conditions and vehicle states. By modifying calibration data in real-time based on sensor feedback and online learning, the system adapts to varying work site conditions without requiring complex manual reconfiguration of each control surface
3Adaptability or versatility
If online learning models are used to determine optimal control paths, then adaptability to changing soil parameters improves, but measurement precision requirements increase to accurately assess action results
Solution Approach 1:
The system implements feedback mechanisms where sensors measure the actual results of earth moving actions (such as soil displacement, tool position, and vehicle state) and use this information to update online learning models. The feedback loop continuously refines the model's understanding of soil parameters and vehicle responses, improving adaptability while managing measurement requirements through iterative learning
Data Source
AI summary
In some implementations, the EMV uses a calibration to inform autonomous control over the EMV. To calibrate an EMV, the system first selects a calibration action comprising a control signal for actuating a control surface of the EMV. Then, using a calibration model comprising a machine learning model trained based on one or more previous calibration actions taken by the EMV, the system predicts a response of the control surface to the control signal of the calibration action. After the EMV executes the control signal to perform the calibration action, the EMV system monitors the actual response of the control signal and uses that to update the calibration model based on a comparison between the predicted and monitored states of the control surface.