Roadway Elevation Map Generation from Laser Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in generating accurate elevation maps of roadways using sensor data, which is crucial for navigation but often includes outliers and incomplete data points, affecting the vehicle's ability to safely and efficiently traverse the terrain.
Innovation Solution
A method and device that process sensor data to generate a 2D grid of the roadway by filtering data points to identify the lowest relative elevation for each cell, using techniques such as outlier removal, interpolation, and clustering to create a reliable elevation map, which can be used to navigate the vehicle.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If sensor data is collected to generate elevation maps, then navigation capability is improved, but data accuracy deteriorates due to outliers and incomplete data points
Solution Approach 1:
The patent extracts and removes outlier data points from the sensor data through filtering processes. The system identifies and eliminates incorrect elevation measurements while retaining valid data points, thereby improving the accuracy of the elevation map without losing the overall navigation capability provided by the comprehensive data set.
Solution Approach 2:
The patent introduces intermediary processing steps including clustering algorithms and interpolation techniques that act as mediators between raw sensor data and final elevation maps. These intermediaries process the data to resolve inconsistencies and fill gaps, transforming inaccurate raw measurements into reliable navigation information.
2Measurement precision
If filtering processes are applied to remove outliers, then data accuracy is improved, but processing complexity increases
Solution Approach 1:
The patent segments the filtering process into distinct stages: initial outlier detection, clustering analysis, and interpolation refinement. By dividing the complex filtering task into manageable segments, the system achieves high data accuracy while keeping each processing stage relatively simple and computationally efficient.
Solution Approach 2:
The patent implements self-service mechanisms where the data processing system automatically identifies and corrects its own errors through adaptive filtering. The system uses the data itself to determine filtering parameters and thresholds, eliminating the need for complex external configuration and reducing overall processing complexity.
3Loss of information
If interpolation is used to fill incomplete data, then map completeness is improved, but risk of introducing errors increases
Solution Approach 1:
The patent employs feedback mechanisms where interpolated data points are validated against surrounding measurements and physical constraints. The system continuously refines interpolations based on feedback from multiple data sources and consistency checks, ensuring that completed data maintains high reliability while achieving full map coverage.
Data Source
AI summary
Aspects of the present disclosure relate generally to generating elevation maps. More specifically, data points may be collected by a laser moving along a roadway and used to generate an elevation map of the roadway. The collected data points may be projected onto a two dimensional or “2D” grid. The grid may include a plurality of cells, each cell of the grid representing a geolocated second of the roadway. The data points of each cell may be evaluated to identify an elevation for the particular cell. For example, the data points in a particular cell may be filtered in various ways including occlusion, interpolation from neighboring cells, etc. The minimum value of the remaining data points within each cell may then be used as the elevation for the particular cell, and the elevation of a plurality of cells may be used to generate an elevation map of the roadway.