LiDAR Ground Path Identification for Autonomous Vehicle Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional LiDAR data processing techniques, such as height thresholding, struggle to reliably differentiate between ground and objects/hazards due to dynamic vehicle motion and non-flat driving surfaces, leading to inaccurate environmental mapping for autonomous vehicles.
Innovation Solution
A method for processing LiDAR data that identifies candidate ground paths and range measurements as ground or non-ground points by decomposing data into height and ground projections, computing differentials, and applying path and point criteria to distinguish between ground and objects, thereby improving discrimination in real-world conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If height thresholding is used to classify objects, then processing speed is maintained, but reliability of ground vs. object differentiation deteriorates due to dynamic vehicle motion and non-flat surfaces
Solution Approach 1:
The patent segments the LiDAR data processing into distinct functional modules: coordinate transformation module (converting LiDAR coordinates to vehicle coordinates), ground path identification module (identifying candidate ground paths), and point classification module (classifying points as ground or non-ground). This segmentation allows each module to handle specific aspects of the complex processing task independently, improving reliability while managing complexity through modular design.
Solution Approach 2:
The patent performs preliminary coordinate transformation and ground path identification before final point classification. By pre-processing the data to establish a transformed coordinate system and identify candidate ground paths in advance, the system creates a structured foundation that improves the reliability of subsequent object differentiation without requiring complex real-time processing during classification.
2Measurement precision
If conventional height thresholding is applied, then processing simplicity is maintained, but measurement precision deteriorates in real-world environmental conditions
Solution Approach 1:
The patent introduces an intermediary coordinate transformation step that converts LiDAR measurements into a vehicle-centric coordinate system before ground detection. This intermediary transformation acts as a mediator that accounts for dynamic vehicle motion and varying terrain, thereby improving measurement precision without requiring the final detection algorithm to directly handle the complexity of raw LiDAR data in moving coordinates.
Solution Approach 2:
The patent changes the parameter space by transforming from absolute LiDAR coordinates to relative vehicle coordinates, and further to ground-referenced coordinates. This parameter transformation adapts the detection framework to real-world conditions by expressing all measurements relative to the moving vehicle and varying ground plane, improving precision while managing complexity through systematic parameter changes.
3Manufacturing precision
If simple height-based classification is used, then processing time is reduced, but accuracy of environmental mapping deteriorates
Solution Approach 1:
The patent segments the environmental mapping process into hierarchical stages: first transforming coordinates, then identifying ground paths, and finally classifying points. This segmentation allows the system to achieve high mapping accuracy through multiple specialized processing steps rather than a single complex operation, balancing precision requirements with time efficiency through divide-and-conquer processing.
Solution Approach 2:
The patent performs preliminary coordinate transformation and ground path identification before final point classification and environmental mapping. By preparing the data structure and establishing reference frames in advance, the system reduces the computational burden during the actual mapping phase, achieving high accuracy without excessive processing time in the critical mapping step.
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 enables robust and reliable discrimination between ground and objects, enhancing the accuracy of environmental mapping for autonomous navigation and parking operations, even in dynamic and non-flat environments.
Implementation Method 1
LiDAR sensors can be particularly useful for mapping the environment (e.g., by generating a three-dimensional point cloud) because laser range measurements are particularly accurate
Implementation Method 2
laser range measurements are particularly accurate and can be generated with reasonable speed required for autonomous or partial autonomous operations
Data Source
AI summary
Improved processing of sensor data (e.g., LiDAR data) can be used to distinguish between free space and objects/hazards. Autonomous vehicles can use such information for performing autonomous driving and/or parking operations. LiDAR data can include a plurality of range measurements (e.g., forming a 3D point cloud). Each of the range measurements can correspond to a respective LiDAR channel and azimuth angle. The processing of LiDAR data can include identifying one or more paths as candidate ground paths based on one or more path criteria. The processing of LiDAR data can also include identifying one or more of the plurality of range measurements as ground points or non-ground points based on the one or more paths identified as candidate ground paths and based on one or more point criteria.