Map Scaffolds for Globally Consistent Vehicle Trajectories
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicle mapping systems face challenges in generating globally consistent maps, leading to inaccuracies and complexities when operating across multiple submaps, due to the lack of global consistency in trajectory data, which affects navigation and routing operations.
Innovation Solution
A georeferenced trajectory system that uses a scaffold to align and transform sensor data from multiple vehicles into a common coordinate frame, ensuring global consistency by creating a geometrically sparse but globally consistent map framework, anchored to survey points for accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If graph-based maps with separate submaps are used, then device complexity is reduced and ease of operation is improved, but global consistency is lost leading to localization drift and inaccuracies
Solution Approach 1:
The patent divides the mapping system into two segments: an online phase that generates local submaps with reduced complexity for real-time operation, and an offline phase that performs global consistency optimization to maintain localization accuracy. This segmentation allows the system to benefit from both simplified operational complexity and high localization precision.
Solution Approach 2:
The patent performs preliminary global consistency optimization in an offline phase before actual autonomous vehicle operation. By pre-processing the trajectory data and optimizing the pose graph in advance, the system establishes accurate global relationships between submaps that will be used during online operation, thereby ensuring high localization accuracy without adding real-time computational complexity.
2Adaptability or versatility
If multiple submaps are used for large geographic regions, then adaptability is improved, but global consistency is lost introducing higher complexity and inaccuracies
Solution Approach 1:
The patent introduces a pose graph optimization process as an intermediary between submap generation and navigation operations. This intermediary offline processing step establishes reliable global transformations between multiple submaps, ensuring that navigation across large geographic regions remains accurate and reliable while maintaining the adaptability benefits of using multiple submaps.
3Measurement precision
If trajectory data is collected from multiple vehicles over time, then measurement precision is improved, but global consistency deteriorates due to accumulated drift
Solution Approach 1:
The patent implements a feedback mechanism through loop closure detection and pose graph optimization. When trajectories from multiple vehicles overlap or form closed loops, the system detects these loops and uses them to correct accumulated drift and inconsistencies. This feedback process continuously refines the global consistency of the map while preserving the high measurement precision gained from multiple data sources.
Data Source
AI summary
A georeferenced trajectory system for vehicles receives trajectory data generated by a plurality of vehicle sensors and scaffolds of previously generated maps and aligns geometry data for a geographic region and trajectory data from the received data from different map builds. A scaffold of a geographic region to be mapped during an initial map build is generated, and the trajectory data from respective map builds is aligned with the scaffold of previously generated maps to generate a map of the geographic region. The resulting map expands the coverage of the existing map such that old and new map data is in a common consistent reference frame whereby the map may be built incrementally by merging or expanding local scaffolds and filling in the merged or expanded scaffold while ensuring global consistency.