Ground Intensity LiDAR Registration for Degenerate-Area Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional LIDAR localization systems struggle in areas with insufficient geometric constraints, such as tunnels and bridges, where they cannot guarantee accurate pose estimation due to the lack of diverse geometric features, leading to multiple valid solutions and reduced reliability.
Innovation Solution
The introduction of a ground intensity LIDAR localizer that complements conventional geometric localization by using LIDAR intensity information to produce pose estimates, enabling 6-degrees-of-freedom localization in geometrically degenerate areas by fusing intensity and geometric data, and running asynchronously with existing localization systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional geometric LIDAR localization is used, then localization works well in areas with diverse geometric features, but it fails in geometrically degenerate areas such as tunnels and bridges
Solution Approach 1:
The patent combines geometric LIDAR data with intensity LIDAR data to create a hybrid localization system. The geometric localizer processes spatial coordinates while the intensity localizer processes reflectivity values, and both are fused to produce a unified pose estimate. This merging allows the system to maintain reliability in geometrically degenerate areas where geometric features are insufficient.
Solution Approach 2:
The patent introduces intensity values as an additional dimension of information beyond the traditional 3D geometric coordinates. By adding this fourth dimension (intensity/reflectivity) to the localization data space, the system gains additional constraints for pose estimation that are independent of geometric complexity, enabling operation in tunnels and bridges.
2Reliability
If ground intensity LIDAR localizer is added to complement conventional localization, then localization reliability in geometrically degenerate areas is improved, but system complexity increases
Solution Approach 1:
The localization system is segmented into independent modules: a geometric localizer that processes spatial data, an intensity localizer that processes reflectivity data, and a fusion component that combines their outputs. Each module operates independently with its own processing pipeline, making the overall system more manageable and maintainable despite the added complexity.
Solution Approach 2:
The intensity localizer is designed to work in conjunction with the geometric localizer, creating a multi-functional localization system. The same intensity data can be used both to complement geometric features in degenerate areas and to provide additional constraints in normal areas, maximizing the utility of the added component.
3Measurement precision
If 6-degrees-of-freedom localization is implemented using intensity data, then pose estimation accuracy is improved in geometrically degenerate areas, but computational requirements increase
Solution Approach 1:
The system uses a histogram filter that operates with partial computational effort compared to more exhaustive methods like grid search. The histogram filter provides sufficient accuracy for 6-DOF localization without requiring the full computational resources of alternative approaches, achieving a practical balance between precision and power consumption.
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.