Vehicle Trajectory Alignment for Globally Consistent Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicle systems face challenges in generating globally consistent maps due to the lack of alignment and accuracy in trajectory data from various sensor logs, which affects navigation and map creation, especially in dynamic environments and urban areas.
Innovation Solution
A georeferenced trajectory estimation system that aligns sensor data from multiple vehicles into a common coordinate frame using GPS spline estimation, cross-registration, LIDAR alignment, pose graph optimization, and trajectory optimization, ensuring global consistency and accuracy by anchoring maps to survey points.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If graph-based maps with separate reference frames are used, then device complexity is reduced and ease of operation is improved, but global consistency across trajectories is lost
Solution Approach 1:
The system divides the mapping problem into local graph-based submaps that maintain operational simplicity, while introducing a global reference frame that ties all submaps together through trajectory alignment, thus preserving both local ease of operation and global consistency
Solution Approach 2:
A global reference frame acts as an intermediary between separate local submaps, providing a common coordinate system that enables consistent positioning across the entire map while allowing local graph structures to maintain their operational simplicity
2Ease of operation
If GPS data is used for trajectory estimation, then ease of operation is improved and device complexity is reduced, but measurement precision and reliability deteriorate due to systematic errors
Solution Approach 1:
The system uses feedback from multiple data sources (LIDAR, visual odometry, inertial sensors) to correct GPS trajectory errors, continuously refining the estimated trajectory by comparing predicted positions with actual sensor measurements and adjusting accordingly
Solution Approach 2:
The trajectory estimation uses a composite approach combining multiple sensor data types (GPS, LIDAR, visual odometry, inertial measurements) to create a more accurate and reliable trajectory estimate than any single source could provide alone
3Loss of information
If multiple sensor logs from different vehicles are combined, then map coverage and information completeness are improved, but trajectory alignment difficulty and device complexity increase
Solution Approach 1:
The system implements a universal alignment framework that can process and align trajectories from multiple vehicle types and sensor configurations using the same reference frame and alignment algorithms, enabling multi-source data integration without requiring vehicle-specific processing pipelines
Data Source
AI summary
A georeferenced trajectory estimation system for vehicles receives trajectory data generated by a plurality of vehicle sensors and fixed reference points of previously generated maps and aligns geometry data for a geographic region and trajectory data from the received data from different map builds. The trajectory data from respective map builds is aligned with fixed reference points of previously generated maps to generate a map of the geographic region. The received map data may include submap or spatially indexed data that is used to provide estimates of where a vehicle in an unmapped area is located by generating a series of pose estimates relating back to a fixed reference point in a previously mapped area. 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 while ensuring global consistency.