Mapped Drivable Paths From Aggregated Road Topography Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating due to the vast volume of data needed for traditional mapping, which can limit or adversely affect navigation, and the sheer quantity of data required for storage and updates poses daunting challenges.
Innovation Solution
A system and method for generating map information using drive information from multiple vehicles, aggregating indicators of road topography features, and generating an image representation of road topography to create target trajectories, which are stored in a map for navigation by host vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional mapping technology is used to navigate autonomous vehicles, then navigation coverage and route options are improved, but data storage requirements and processing burden increase significantly
Solution Approach 1:
The patent extracts only the essential navigation elements (drivable paths, road boundaries, obstacles) from comprehensive map data, discarding redundant information. This selective extraction reduces data volume while preserving navigation functionality, directly resolving the contradiction between navigation coverage and data storage requirements
Solution Approach 2:
The mapping process is segmented into multiple stages: data collection from multiple vehicles, aggregation of drive information, generation of image representations, and creation of drivable paths. This segmentation allows progressive refinement of map data, reducing overall data volume while maintaining navigation quality
2Measurement precision
If comprehensive map data is stored and updated for autonomous navigation, then navigation accuracy is improved, but storage costs and update complexity increase
Solution Approach 1:
The patent merges drive information from multiple vehicles traversing the same road segment, aggregating their sensors and cameras data. This combination improves navigation accuracy through multiple observations while distributing the data collection burden across many vehicles, reducing individual vehicle complexity and overall system update complexity
Solution Approach 2:
Instead of storing and processing raw sensor data from each vehicle, the system creates compressed image representations that capture essential road topography features. This copying approach preserves navigation accuracy while dramatically reducing storage requirements and update complexity
3Reliability
If autonomous vehicles process vast volumes of sensor data in real-time, then navigation decision quality is improved, but processing time and computational load increase
Solution Approach 1:
The system performs preliminary processing of sensor data by multiple vehicles during their normal operation, aggregating and processing drive information before it is needed for navigation decisions. This advance processing reduces real-time computational load while maintaining high navigation decision quality
Solution Approach 2:
The patent replaces complex real-time mechanical processing of raw sensor data with pre-processed image representations and aggregated drive information. This substitution reduces computational complexity and processing time while preserving the reliability needed for safe navigation decisions
Data Source
AI summary
A system for generating map information for use in navigating a host vehicle relative to a road segment may include at least one processor comprising circuitry and a memory. The at least one processor receives drive information from each of a plurality of vehicles that traversed a road segment. The drive information may include indicators representative of road topography features associated with the road segment. The indicators may be aggregated, and an image representation of road topography of the road segment based on the aggregated indicators may be generated. The image representation may be provided as input to at least one trained model configured to generate an output including at least one target trajectory for the road segment. The at least one target trajectory may be stored in a map. The map may be provided to at least one host vehicle navigation system for use in navigating the host vehicle.