Sparse Factor Graph Mapping for Autonomous Vehicle Data Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face inefficiencies in transmitting, storing, and processing large amounts of environmental and map data, which can lead to resource-intensive and time-consuming navigation, especially in updating data for changing environments.
Innovation Solution
The system employs a sparse data graph or factor graph representation of environmental and map data, indexed by geographic regions, allowing for efficient storage and processing by linking nodes based on shared trajectories, sensor data, and geographic positions, enabling quick updates and optimization of data without requiring the parsing of entire datasets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If large amounts of environmental and map data are transmitted and stored, then navigation accuracy is improved, but resource consumption and processing time increase
Solution Approach 1:
The patent extracts and stores only the essential geometric features (points, lines, polygons) from environmental data, removing redundant information. This selective extraction maintains navigation accuracy while significantly reducing the volume of data that needs to be transmitted and processed, thereby lowering resource consumption.
Solution Approach 2:
The patent segments environmental data into distinct geometric primitives (points, lines, polygons) that can be independently stored and processed. This segmentation allows the system to handle data in manageable units, reducing overall processing time and resource requirements while preserving the necessary spatial information for accurate navigation.
2Measurement precision
If large amounts of environmental and map data are transmitted and stored, then navigation accuracy is improved, but processing time increases
Solution Approach 1:
The patent extracts only the critical geometric features from environmental data, eliminating redundant information. This extraction process maintains the precision needed for accurate navigation while dramatically reducing the amount of data that must be processed, thereby decreasing processing time.
Solution Approach 2:
The patent transforms complex environmental data into simplified geometric parameters (coordinates of points, lines, and polygons). This parameter transformation reduces data complexity and size, enabling faster processing while preserving the spatial accuracy required for navigation.
3Loss of information
If complete environmental data is stored, then data completeness is improved, but storage requirements and processing overhead increase
Solution Approach 1:
The patent extracts essential geometric information from complete environmental data, storing only the necessary features (points, lines, polygons) rather than the full dataset. This extraction maintains data completeness for navigation purposes while significantly reducing storage requirements and processing overhead.
Solution Approach 2:
The patent segments environmental data into discrete geometric primitives that can be stored and processed independently. This segmentation reduces the complexity of data management and processing while preserving the complete spatial information needed for accurate navigation.
Data Source
AI summary
Techniques associated with generating and maintaining sparse geographic and map data. In some cases, the system may maintain a factor graph comprising a plurality of nodes. In some cases, the nodes may comprise pose data and sensor data associated with an autonomous vehicle at the geographic position represented by the node. The nodes may be linked based on shared trajectories and shared sensor data.