Vehicle GPR Localization Using Surface and Underground Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately localizing themselves on roads due to unreliable road surface features and the inability of standard sensors to detect underground features, especially in adverse weather conditions.
Innovation Solution
The use of ground-penetrating radar (GPR) sensors to transmit pulsed electromagnetic signals and detect both road surface and underground features, generating shallow-GPR and deep-GPR data to improve localization accuracy by creating maps of underground features, which can be used in conjunction with surface features for navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If standard sensors (camera, LiDAR, radar) are used for vehicle localization, then the system is simple and cost-effective, but localization accuracy deteriorates in adverse weather conditions and underground features cannot be detected
Solution Approach 1:
The patent combines multiple sensing modalities (GPR, camera, LiDAR, radar) into a unified sensor fusion system. The GPR sensor is integrated with existing autonomous vehicle sensors to create a comprehensive perception system that leverages the strengths of each sensor type for improved localization accuracy in adverse conditions
Solution Approach 2:
The GPR sensor acts as an intermediary that detects underground features (rebar, utilities) which serve as stable reference points for localization. These underground features provide a reliable coordinate system that mediates between the vehicle's sensor data and the actual road position, enabling accurate localization when surface features are unreliable
2Reliability
If GPR sensors are added to detect underground features, then localization reliability improves, but device complexity and cost increase
Solution Approach 1:
The system performs preliminary mapping of underground features using GPR to create a prior database of subsurface infrastructure (rebar patterns, utilities). This preliminary action enables the vehicle to compare real-time GPR readings against the pre-established underground feature map, improving localization reliability without requiring complex real-time processing during vehicle operation
Solution Approach 2:
The system implements feedback loops where GPR data is continuously compared against the underground feature map to refine localization estimates. The feedback mechanism allows the system to correct positioning errors by detecting deviations from expected underground feature patterns, thereby improving reliability while managing complexity through iterative refinement
3Measurement precision
If shallow-GPR filtering is used to identify road surface features, then surface feature detection accuracy improves, but deep underground feature detection capability is reduced
Solution Approach 1:
The patent segments the GPR signal processing into distinct filtering pathways: shallow-GPR filtering for surface features (asphalt conditions, road markings) and deep-GPR filtering for underground features (rebar, utilities). This segmentation allows each filtering process to be optimized for its specific depth range without compromising the other, preserving both surface and subsurface information through separate processing channels
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
Enhances the accuracy of vehicle localization, particularly in adverse weather conditions, by utilizing GPR data to identify and map underground features, providing a more reliable method for navigation compared to traditional sensors.
Implementation Method 1
activating a ground-penetrating radar (GPR) sensor on a vehicle to transmit a pulsed electromagnetic signal toward a ground surface
Implementation Method 2
receiving the pulsed electromagnetic signal reflected from the road surface features and underground features by the GPR sensor
Data Source
AI summary
The present technology is directed to identifying road surface features and underground features using a ground-penetrating radar (GPR) sensor. The present technology may include activating the GPR sensor on a vehicle to transmit a pulsed electromagnetic signal toward a ground surface. The present technology may also include receiving the pulsed electromagnetic signal reflected from the road surface features and underground features by the GPR sensor. The present technology may also include filtering the pulsed electromagnetic signal to generate a shallow-GPR data or deep-GPR data, wherein the shallow-GPR data is used to identify the road surface features and the deep-GPR is used to identify the underground features. The present technology may also include adjusting operational parameters based on at least one of the road surface features and the underground features.