HD Map Updates Using Low-Resolution Fleet Map Assets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional autonomous vehicle map updates are inefficient, requiring days to weeks for data collection and processing, leading to latency and reduced routability, which increases trip time and operational costs.
Innovation Solution
The solution involves updating high definition maps using low resolution map assets, leveraging data collected by autonomous vehicles to generate updated map tiles and semantic labels, reducing the need for mapping cars and improving data collection efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional mapping cars are used to collect high resolution map data, then map accuracy is improved, but map update time increases to days or weeks
Solution Approach 1:
The patent creates low resolution copies of map data from autonomous vehicle sensor data to quickly update map information without requiring full high resolution mapping car operations. These low resolution map copies provide sufficient information for routing decisions while dramatically reducing update time from days/weeks to minutes/hours.
Solution Approach 2:
The patent applies partial action by using only the necessary portion of full map data - specifically low resolution versions that contain sufficient information for navigation and routing decisions. This partial data approach maintains adequate map accuracy for operational needs while eliminating the time-consuming collection and processing of complete high resolution data.
2Reliability
If mapping cars are deployed for frequent map updates, then map freshness is improved, but operational costs increase
Solution Approach 1:
The patent makes autonomous vehicles serve multiple functions: their primary ride-sharing function plus a secondary map data collection function. By utilizing the sensor data already being collected during normal operations, the system achieves frequent map updates without deploying dedicated mapping cars, thereby maintaining map freshness while avoiding additional operational costs.
Solution Approach 2:
The system uses the autonomous vehicles' own sensor data to update maps, making the fleet self-sufficient for map maintenance. This self-service approach eliminates the need for separate mapping car deployments, achieving both map freshness and cost efficiency simultaneously.
3Measurement precision
If high resolution map data is collected and processed, then routing accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
The patent applies local quality by providing different resolution levels of map data for different purposes. Low resolution data is used for general routing decisions where high precision is not critical, while high resolution data is reserved for specific areas or situations requiring detailed accuracy. This differentiated approach reduces overall processing time and computational resources while maintaining adequate routing accuracy.
Data Source
AI summary
The disclosed technology provides solutions for updating high definition maps based on low resolution map assets. In some aspects, a process of receiving a change detection relating to a change in the real world is provided. The process can include steps for receiving autonomous vehicle drive data based on the change in the real world, generating low resolution tile data based on the autonomous vehicle drive data based on the change in the real world, generating updated semantic data based on the low resolution tile data generated, and providing the updated semantic data to an autonomous vehicle to update a proximate area of the change in the real world of a base map of the autonomous vehicle. Systems and machine-readable media are also provided.