Road Surface Sensor Mapping for Robust Vehicle Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional vehicle localization techniques, such as SLAM, often result in imprecise positioning, leading to poor navigation and increased risks due to their lack of robustness and accuracy.
Innovation Solution
The use of sensor maps, specifically acoustic and acceleration maps generated by a fleet of vehicles, to segment geographic regions into grids and associate sensor fingerprints with cells, allowing for more accurate vehicle localization through correlation of sensor data with pre-defined fingerprints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional SLAM techniques are used for vehicle localization, then the system can operate with standard sensors and algorithms, but the positioning accuracy and robustness deteriorate
Solution Approach 1:
The geographic region is segmented into a grid of cells, with each cell containing sensor fingerprints collected by fleet vehicles. This segmentation allows the system to divide the localization problem into manageable discrete units, improving both accuracy and robustness by enabling cell-by-cell matching rather than relying solely on continuous SLAM algorithms.
Solution Approach 2:
Sensor fingerprints are pre-collected and stored in map cells before vehicles need localization. The fleet vehicles traverse geographic regions and accumulate sensor data (acoustic, acceleration, optical) that are stored as fingerprints in corresponding grid cells. When a vehicle needs localization, it compares its current sensor readings against these pre-stored fingerprints, eliminating the need for real-time SLAM computation and significantly improving positioning accuracy and robustness.
2Measurement precision
If sensor maps with acoustic and acceleration data are implemented, then localization accuracy improves, but system complexity increases
Solution Approach 1:
The sensor map system uses multiple sensor types (acoustic, acceleration, optical) that serve multiple functions: acoustic sensors capture tire-road interaction sounds for fingerprinting, acceleration sensors detect road surface characteristics, and optical sensors provide visual confirmation. This multi-functionality allows a single infrastructure to support various localization scenarios and environmental conditions, improving accuracy without proportionally increasing complexity.
Solution Approach 2:
Fleet vehicles automatically collect and contribute sensor data to build and update the sensor map without requiring manual intervention. As vehicles traverse geographic regions, their sensors continuously gather acoustic, acceleration, and optical data that are automatically processed and stored as fingerprints in the appropriate grid cells. This self-service mechanism distributes the mapping workload across the entire fleet, reducing the complexity burden on any single vehicle or central system.
Data Source
AI summary
Systems, methods, and non-transitory computer-readable media can determine sensor data collected by a fleet of vehicles while navigating a geographic region, the sensor data including sensor readings generated at least in part by a surface interaction between one or more tires of each of the fleet of vehicles and a road surface of the geographic region. A sensor map representing the geographic region can be determined. The map can segment the geographic region into a grid of cells. Instances of the collected sensor data can be associated with cells in the grid of cells. A corresponding fingerprint can be determined for one or more cells in the grid of cells based at least in part on a plurality of instances of sensor data associated with the cell.