Crowdsourced Road Alignment for Sparse Vehicle Navigation Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating effectively due to the vast amounts of data they need to process and store for navigation, including visual information, GPS data, and sensor data, which can lead to inefficiencies and safety concerns.
Innovation Solution
The use of cameras for navigation with a crowdsourced sparse map, aligning navigation information from multiple vehicles, and fusing data from various sources like cameras, sensors, and maps to optimize navigation while ensuring safety.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional mapping technology is used for autonomous vehicle navigation, then navigation accuracy is improved, but data storage requirements and processing complexity increase significantly
Solution Approach 1:
The patent extracts and utilizes only the essential navigational features from road environments (lane markings, road geometry, intersections) to create sparse maps, rather than storing complete traditional map data. This selective extraction maintains navigation accuracy while dramatically reducing data storage requirements
Solution Approach 2:
Instead of vehicles receiving pre-defined detailed maps from central servers, the system inverts the approach by having vehicles contribute their own observed road features to collectively build sparse maps. This distributed map construction reduces individual vehicle data storage needs while maintaining comprehensive coverage
2Reliability
If complete map data is stored and updated continuously, then navigation reliability is improved, but system complexity and update challenges increase
Solution Approach 1:
The sparse map system dynamically adapts to road changes by continuously receiving and processing navigational information from multiple vehicles. The map structure evolves automatically as vehicles encounter new road features or changes, eliminating the need for manual map updates while maintaining reliability
Solution Approach 2:
The patent merges navigational observations from multiple vehicles to construct and update sparse maps collectively. By combining data from several sources, the system achieves reliable navigation information without requiring complex individual vehicle systems or centralized map management
3Measurement precision
If navigational information from multiple vehicles is collected and aligned, then map accuracy and coverage are improved, but data processing time and computational resources increase
Solution Approach 1:
The patent segments the road environment into distinct navigational features (lane markings, intersections, road geometry) that can be independently identified and processed. This segmentation allows vehicles to process only relevant features rather than complete image data, reducing processing time while maintaining map accuracy
Solution Approach 2:
Instead of processing and storing complete image data from multiple vehicles, the system extracts and stores simplified representations (copies) of road features. These feature copies retain essential navigational information while requiring minimal processing and storage resources
Data Source
AI summary
The present disclosure relates to systems and methods for aligning navigation information from a plurality of vehicles. In one implementation, at least one processing device may receive first navigational information from a first vehicle and second navigational information from a second vehicle. The first and second navigational information may be associated with a road segment. The processor may divide the first navigational information into at least a first portion and a second portion; divide the second navigational information into at least a first portion and a second portion; align the first portion of the first navigational information with the first portion of the second navigational information; align the second portion of the first navigational information with the second portion of the second navigational information; generate a road model based on the aligned portions; and send the road model to vehicles for use in navigating along the road segment.