LIDAR Sensor Localization via Reference Pose Graph
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
LIDAR sensors struggle to provide accurate data in urban environments due to limited precision in locating the sensor, which affects the reliability of object mapping and vehicle navigation.
Innovation Solution
A method using a mapping vehicle with a mobile LIDAR sensor to generate a reference pose graph from point cloud data, aligning it with data from stationary infrastructure nodes, allowing for precise localization of the LIDAR sensor to within centimeters, and transmitting object locations to vehicles for autonomous operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS sensors are used to locate LIDAR sensors, then the location can be obtained, but the precision is insufficient (accuracy of at best within a few meters)
Solution Approach 1:
The patent introduces an intermediary calibration process using a mobile LIDAR sensor to create a reference pose graph that mediates between GPS coordinates and actual LIDAR sensor positions. This reference pose graph serves as a mediator to transform imprecise GPS locations into precise centimeter-level positioning by matching LIDAR point cloud data with the reference graph, thereby resolving the contradiction between using simple GPS and achieving high precision.
2Reliability
If LIDAR sensor location is not precisely known, then the system is simpler to implement, but the LIDAR data reliability deteriorates
Solution Approach 1:
The patent applies preliminary action by pre-establishing a reference pose graph through mobile LIDAR scanning before deploying stationary LIDAR sensors. This pre-created reference graph contains precise spatial information about the environment, which is then used to calibrate and locate stationary LIDAR sensors. By performing this calibration action in advance, the system achieves high reliability LIDAR data without requiring complex real-time localization mechanisms at each sensor node.
Data Source
AI summary
A reference pose graph can be generated from first point cloud data collected at each of a plurality of mobile nodes. A location of a stationary node can be specified based on the reference pose graph and second point cloud data collected by the stationary node.