Ground Intensity LiDAR Registration for Degenerate Road Geometry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional LIDAR localization systems struggle in geometrically degenerate areas such as tunnels, bridges, and highways, where insufficient geometric features lead to ambiguous pose estimates, limiting their ability to provide accurate 6-degree-of-freedom localization.
Innovation Solution
The integration of ground intensity LIDAR data to complement geometric information, allowing for simultaneous operation of intensity and geometric localizers, which fuse map-relative pose estimates to enhance localization accuracy and robustness in degenerate areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional geometric LIDAR localization is used, then localization works well in environments with rich geometric features, but it fails in geometrically degenerate areas such as tunnels, bridges, and highways
Solution Approach 1:
The patent combines geometric LIDAR data with intensity LIDAR data to create a hybrid localization system. The geometric localizer processes 3D point cloud geometry while the intensity localizer processes reflectance intensity values, and both estimates are fused to achieve reliable localization in geometrically degenerate environments where one method alone would fail.
Solution Approach 2:
The localization system is designed to operate universally across different environment types by implementing multiple localization methods (geometric and intensity-based) that can adapt to various conditions. The system automatically selects or fuses methods based on environmental characteristics, making it versatile for highways, tunnels, bridges, and urban areas.
2Measurement precision
If only geometric LIDAR data is used for localization, then the system is simpler to implement, but it cannot provide accurate pose estimates in areas with insufficient geometry
Solution Approach 1:
The patent merges geometric LIDAR processing with intensity LIDAR processing into a unified localization framework. Both geometric features and intensity reflectance are extracted from the same LIDAR measurements and processed through separate but complementary localization algorithms, improving accuracy without requiring additional sensors.
Solution Approach 2:
The system utilizes a different parameter (intensity reflectance) in addition to the traditional geometric parameters. By changing from purely spatial coordinates to including optical property measurements, the system gains additional information for pose estimation in environments where geometric features are insufficient.
3Reliability
If intensity LIDAR data is integrated to complement geometric information, then localization accuracy improves in degenerate areas, but computational complexity increases
Solution Approach 1:
The localization system is segmented into independent geometric and intensity processing modules. Each module operates separately on its respective data type and produces an independent pose estimate, which are then fused. This modular approach manages computational complexity by allowing parallel processing and independent optimization of each module.
Solution Approach 2:
A pose filter acts as an intermediary that fuses the estimates from the geometric localizer and intensity localizer. This mediator combines the two independent localization results using probabilistic methods, managing the computational complexity of fusion while improving overall reliability through the complementary nature of the two estimation methods.
Data Source
AI summary
A system for determining a pose of a vehicle and building maps from vehicle priors processes received ground intensity LIDAR data including intensity data for points believed to be on the ground and height information to form ground intensity LIDAR (GIL) images including pixels in 2D coordinates where each pixel contains an intensity value, a height value, and x- and y-gradients of intensity and height. The GIL images are formed by filtering aggregated ground intensity LIDAR data falling into a same spatial bin on the ground and using a registration algorithm to align two GIL images relative to one another by estimating a 6-degree-of-freedom pose with associated uncertainty that minimizes error between the two GIL images. The aligned GIL images are provided as a pose estimate to a localizer. The system may provide online localization and pose estimation, prior building, and prior to prior alignment pose estimation using image-based techniques.