Traffic Light Orientation Mapping From Crowdsourced Landmark Clusters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating due to the sheer volume of data needed to process, store, and update maps, particularly when relying on traditional mapping technologies.
Innovation Solution
The system aggregates drive information from multiple vehicles to identify landmark clusters and determine location identifiers for actual landmarks, which are then used to update a map and guide autonomous vehicles in navigating along road segments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional mapping technology is used to navigate autonomous vehicles, then navigation accuracy is improved, but data storage and processing requirements increase significantly
Solution Approach 1:
The patent extracts only the essential navigational elements (landmarks and their orientations) from complete traditional maps. Instead of storing and processing entire map datasets, the system identifies and stores only critical reference points that enable navigation, significantly reducing data requirements while maintaining navigational functionality
Solution Approach 2:
The patent applies local quality by focusing computational and storage resources on specific critical locations (landmarks) rather than uniformly processing entire map areas. Each landmark is individually characterized by its orientation and positional relationships, allowing efficient local navigation decisions without global map processing
2Loss of information
If traditional mapping technology is used to navigate autonomous vehicles, then complete environmental information is obtained, but data processing complexity increases
Solution Approach 1:
The system extracts only the most salient environmental features (landmarks with identifiable orientations) from the complete environmental dataset. By filtering out non-essential information and retaining only orientation-critical landmarks, the system reduces processing complexity while preserving navigationally relevant environmental data
Solution Approach 2:
The patent segments the continuous environmental map into discrete, independent landmark entities. Each landmark is processed as a separate unit with its own orientation characteristics, allowing modular and efficient processing compared to handling continuous map data
3Measurement precision
If crowd-sourced drive information from multiple vehicles is aggregated, then map accuracy is improved, but data volume increases
Solution Approach 1:
The patent merges orientation information from multiple vehicle detections of the same landmark into a single consolidated landmark record. By combining observations from multiple sources and averaging or voting on orientation values, the system improves accuracy while storing only one representative record per landmark rather than multiple redundant observations
Solution Approach 2:
The system creates simplified copies of landmark information that capture essential navigational properties (position and orientation) without replicating complete sensor datasets. Each landmark serves as a compressed representation of multiple observations, enabling accurate navigation with reduced data storage
Data Source
AI summary
Systems and methods may detect objects. In one implementation, a method may include obtaining drive information captured during drives by a plurality of vehicles traversing or having traversed a road segment. The drive information for each of the plurality of vehicles may include a drive identifier and landmark detection information corresponding to one or more landmark detections. The landmark detection information included in the obtained drive information from the plurality of vehicles may be aggregated, and based on the aggregated landmark detection information, at least two landmark clusters may be identified. The method may determine, based on the drive identifier associated with the drive information received from each of the plurality of vehicles, a distribution of drive identifiers relative to the at least two landmark cluster and determine, based on the distribution of drive identifiers, a location identifier for one or more actual landmarks positioned along the road segment.