Autonomous Earth-Moving Control Using LiDAR Point-Cloud Perception
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for autonomous control of powered earth-moving vehicles are limited by the use of limited types of sensed data, inability to perform fully autonomous operations when faced with on-site obstacles, and the requirement for bulky and expensive hardware systems, which hinder coordinated operations between multiple vehicles.
Innovation Solution
The implementation of on-vehicle perception systems using LiDAR components and additional sensors to gather and analyze data, generating 3D maps of the environment, and using this data to control autonomous movements and operations, including the movement of vehicle arms and attachments to gather additional data, enabling fully autonomous operations and coordination between vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If limited types of sensed data are used for autonomous control, then device complexity is reduced, but measurement precision and reliability of autonomous operations deteriorate
Solution Approach 1:
The patent combines multiple types of sensors (LiDAR, cameras, radar, ultrasonic sensors, GPS) into a unified perception system that integrates diverse data sources. This merging approach achieves comprehensive environmental awareness and high measurement precision without requiring each individual sensor to be overly complex, resolving the contradiction between device complexity and measurement precision.
Solution Approach 2:
The perception system is designed with multi-functional sensors that can perform multiple detection tasks simultaneously (e.g., LiDAR for both distance measurement and 3D mapping, cameras for both obstacle detection and environmental monitoring). This universality reduces the total number of specialized sensors needed, lowering overall device complexity while maintaining high measurement precision across multiple functions.
2Device complexity
If limited types of sensed data are used, then device complexity is reduced, but the ability to perform fully autonomous operations when faced with obstacles deteriorates
Solution Approach 1:
The patent merges multiple sensor types (LiDAR for depth, cameras for visual recognition, radar for obstacle detection, ultrasonic sensors for proximity) to create a robust perception system. This combination provides redundant and complementary information that significantly improves autonomous operation reliability when facing obstacles, while the integrated architecture keeps overall device complexity manageable.
Solution Approach 2:
The system implements continuous feedback loops where sensor data is constantly processed, analyzed, and used to adjust vehicle operations in real-time. This feedback mechanism enables the autonomous vehicle to respond dynamically to obstacles and changing environments, greatly enhancing operational reliability without requiring excessively complex hardware.
3Measurement precision
If bulky and expensive hardware systems are used to support autonomous operations, then measurement precision and reliability improve, but ease of manufacture and coordination between multiple vehicles deteriorate
Solution Approach 1:
The patent employs universal, multi-functional sensors that can be standardized across different vehicle models and manufacturers. These sensors perform multiple detection functions simultaneously, reducing the total hardware quantity needed and lowering manufacturing costs while maintaining high measurement precision. The standardized approach also facilitates easier coordination between multiple vehicles using the same sensor suite.
Solution Approach 2:
The system uses software-based processing and simulation techniques that can replicate complex sensing capabilities without requiring physically bulky hardware. Digital twins and virtual sensing algorithms allow the system to achieve high measurement precision through computational methods, reducing hardware complexity and manufacturing costs while enabling easier vehicle production and coordination.
4Measurement precision
If more sensors are deployed to gather additional data, then measurement precision and autonomous operation capability improve, but device complexity and cost increase
Solution Approach 1:
The patent merges multiple sensor types into an integrated perception system with unified data processing. This consolidation achieves high measurement precision for environmental mapping by combining the strengths of different sensors (LiDAR for precision depth, cameras for broad coverage, radar for penetration) while managing device complexity through centralized control and coordinated operation.
Solution Approach 2:
The system dynamically adjusts sensor activation and data collection strategies based on operational context. Not all sensors operate at full capacity simultaneously; instead, the system activates specific sensors based on environmental conditions and task requirements. This dynamic approach maintains high measurement precision when needed while reducing average device complexity and power consumption.
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
This approach allows for more accurate and efficient autonomous operations, reduces the need for expensive hardware, and enables the vehicles to navigate and perform tasks with greater precision and safety, even in the presence of obstacles, by utilizing data from various sensors to create detailed environmental maps and adjust operations accordingly.
Implementation Method 1
use one or more LiDAR components to repeatedly map an environment around the vehicle, such as to determine a 3D (three-dimensional) point cloud
Implementation Method 2
one or more LiDAR components that repeatedly (e.g., continuously) map an environment around the vehicle
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 (e.g., of a vehicle's hydraulic arm(s), tool attachment(s), tracks/wheels, rotatable chassis, etc.) to move materials or perform other actions based at least in part on data about an environment around the vehicle(s). A perception system on a vehicle that includes at least a LiDAR component may be used to repeatedly map a surrounding environment and determine a 3D point cloud with 3D data points reflecting the surrounding ground and nearby objects, with the LiDAR component mounted on a component part of the vehicle that is moved independently of the vehicle chassis to gather additional data about the environment. GPS data from receivers on the vehicle may further be used to calculate absolute locations of the 3D data points.