Autonomous Excavator Tool Path Learning for Variable Soil Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The operation of earth moving vehicles is costly and challenging due to the need for manual operators and the complexity of adapting to changing soil conditions and varied vehicle models, which complicates the development of effective autonomous control systems.
Innovation Solution
An autonomous or semi-autonomous earth moving system that uses a combination of sensors and machine learning models to control and navigate earth moving vehicles, selecting optimal tool paths and control signals based on real-time data from the vehicle and environment, allowing for online learning and adaptation to soil parameters and conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual operators control earth moving vehicles, then operational flexibility and adaptability to changing conditions are maintained, but operational costs increase and productivity decreases
Solution Approach 1:
The earth moving vehicle is equipped with sensors and machine learning models that enable it to autonomously sense soil conditions, determine optimal tool paths, and adjust its operation without human intervention. The system serves itself by automatically adapting to changing conditions while maintaining high productivity through continuous operation and optimized decision-making algorithms.
2Productivity
If autonomous control systems are implemented, then productivity and operational efficiency improve, but system complexity increases due to the need for sensors, machine learning models, and real-time data processing
Solution Approach 1:
The autonomous control system is designed with universal machine learning models and sensor integration that can adapt to multiple earth moving vehicle types and various soil conditions. The system performs multiple functions including environmental sensing, tool path optimization, real-time adaptation, and control signal generation within a unified framework, reducing overall system complexity through multi-functionality.
3Adaptability or versatility
If machine learning models are used for tool path optimization, then adaptability to varying soil conditions improves, but computational requirements and processing time increase
Solution Approach 1:
The machine learning models are pre-trained offline with extensive soil condition data and tool path optimization scenarios before deployment. This preliminary training allows the models to quickly infer optimal tool paths in real-time during actual operation, separating the computationally intensive learning phase from the time-critical execution phase, thereby reducing operational processing time while maintaining high adaptability.
4Adaptability or versatility
If multiple earth moving vehicle models are supported, then system versatility improves, but difficulty of developing and maintaining autonomous control increases
Solution Approach 1:
The autonomous control system uses parameterized vehicle models and adaptive machine learning approaches that can accommodate different earth moving vehicle types through configuration of specific parameters rather than requiring separate control systems for each vehicle model. The system adjusts its behavior based on vehicle-specific parameters while maintaining a unified control architecture, simplifying development and maintenance.
Data Source
AI summary
An autonomous earth moving system can select an action for an earth moving vehicle (EMV) to autonomously perform using a tool (such as an excavator bucket). The system then generates a set of candidate tool paths, each illustrating a potential path for the tool to trace as the earth moving vehicle performs the action. In some cases, the system uses an online learning model iteratively trained to determine which candidate tool path best satisfies one or more metrics measuring the success of the action. The earth moving vehicle the executes the earth moving action using the selected tool path and measures the results of the action. In some implementations, the autonomous earth moving system updates the machine learning model based on the result of the executed action.