Autonomous Earth-Moving Vehicle Control Using Simulated Operation Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing earth-moving vehicles face limitations in fully autonomous operations due to limited sensed data, inability to handle on-site obstacles, and the need for bulky and expensive hardware systems, as well as challenges in coordinating multiple vehicles.
Innovation Solution
Implementing autonomous control systems using data from simulated vehicle operations, including machine learning models trained on simulated data to optimize hardware configurations and operation plans, and integrating various sensors for precise obstacle detection and navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If limited types of sensed data are used for autonomous operation, then device complexity is reduced, but the ability to perform fully autonomous operations when faced with on-site obstacles deteriorates
Solution Approach 1:
The patent creates a virtual copy of the construction site environment through simulation, allowing the autonomous vehicle to train and learn obstacle handling strategies in a virtual replica without requiring complex physical sensor arrays. The simulation environment copies real-world conditions including obstacles, terrain, and operational scenarios, enabling the vehicle to develop robust autonomous capabilities through virtual experience rather than physical sensor complexity.
Solution Approach 2:
The system performs preliminary training actions in a simulated environment before actual autonomous operation. The vehicle learns obstacle detection and navigation strategies through extensive virtual practice, preparing the autonomous control system in advance with pre-acquired knowledge about handling various on-site obstacles, thereby reducing the need for complex real-time sensing hardware.
2Measurement precision
If more sensors are added to improve obstacle detection, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The simulation environment creates a virtual copy of the physical environment with accurate representations of obstacles, terrain, and operational conditions. This virtual copying allows the system to achieve high measurement precision for obstacle detection through software-based environmental modeling rather than through proliferation of physical sensors, thereby maintaining detection accuracy while reducing hardware complexity.
3Ease of manufacture
If autonomous control is implemented without simulated operation data, then ease of manufacture is improved, but productivity and operational efficiency deteriorate
Solution Approach 1:
The system performs preliminary training and data generation actions in a simulated environment before actual deployment. By pre-training the autonomous control system using simulated operation data that replicates real-world conditions, the system achieves high operational efficiency and productivity in actual use without requiring complex manufacturing processes or extensive field testing, thereby resolving the contradiction between ease of manufacture and operational efficiency.
4Productivity
If multiple vehicles are coordinated autonomously, then productivity is improved, but device complexity and coordination difficulty increase
Solution Approach 1:
The simulation environment serves multiple functions: it trains individual vehicle autonomous capabilities, models coordination scenarios between multiple vehicles, and generates training data for inter-vehicle communication and collaboration. This universal simulation platform enables multi-vehicle coordination productivity without requiring separate complex coordination hardware for each vehicle, as the simulation collectively develops all necessary coordination strategies.
Data Source
AI summary
Systems and techniques are described for implementing autonomous control of earth-moving construction and/or mining vehicles, including to automatically determine and control autonomous movement of part or all of one or more such vehicles (e.g., a vehicle's arm(s) and/or attachment(s), such as a digging bucket, claw, hammer, blade, etc.) to move materials or perform other actions in a manner that is based at least in part on data from simulated operation of the vehicle(s). For example, the systems/techniques may include using data from simulated operation of the earth-moving vehicle(s) in various manners, such as for use in training one or more machine learning models that are used in implementing the autonomous operations, determining optimal or otherwise preferred hardware component configurations to use, determining optimal or otherwise preferred implementation plans to use for one or more tasks and/or multi-task jobs, enabling user what-if experimentation activities, etc.