Vehicle Pose Estimation Across Sub-Map Transitions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous vehicle systems face challenges in accurately determining vehicle position and attitude changes when transitioning between different sub-maps, leading to inefficiencies in navigation and control.
Innovation Solution
A pose system comprising a pose state estimator and localizers that utilize remote sensor data and motion sensors to determine vehicle poses, with mechanisms for detecting sub-map changes and selecting appropriate sub-maps based on error thresholds and covariance indicators, ensuring seamless transitions between sub-maps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If the vehicle navigates through multiple sub-maps, then the coverage area is improved, but the position determination accuracy deteriorates during transitions
Solution Approach 1:
The patent divides the operational area into multiple sub-maps, each with its own coordinate system and feature set. This segmentation allows the vehicle to operate in larger coverage areas while maintaining position accuracy within each sub-map by using local features for pose estimation during transitions between sub-maps.
Solution Approach 2:
The patent introduces an intermediary mechanism that detects sub-map transitions and propagates coordinate transformations between sub-maps. This intermediary layer ensures that position determination remains accurate during transitions by properly transforming coordinates and selecting appropriate features from the current sub-map.
2Reliability
If multiple localizers are used, then the reliability is improved, but the device complexity increases
Solution Approach 1:
The patent combines multiple localizers (geometric localizer using 3D objects, ground intensity localizer using LIDAR data, and GPS localizer) into a unified pose system. This merging approach improves reliability by using multiple independent methods simultaneously while managing complexity through a centralized pose state estimator that processes inputs from all localizers.
Solution Approach 2:
The pose state estimator serves as a universal component that processes pose estimates from multiple different localizer types. This multi-functional approach allows the system to maintain reliability across diverse sensing modalities while avoiding the complexity of separate processing systems for each localizer.
3Measurement precision
If sub-map transitions are detected, then the position accuracy is improved, but the processing time increases
Solution Approach 1:
The patent performs preliminary actions by pre-defining sub-map boundaries and coordinate transformations before the vehicle reaches transition zones. When a transition is detected, the system can quickly apply pre-computed transformations rather than performing complex real-time calculations, thus maintaining position accuracy while minimizing processing time delays.
Data Source
AI summary
Various examples are directed to systems and methods for locating a vehicle. A pose state estimator may access a previous position for the vehicle at a first time, wherein the previous position is on a first sub-map of a plurality of sub-maps. The pose state estimator may receive from a first localizer a first position estimate for the vehicle at a second time after the first time. The first position estimate may be on a second sub-map of the plurality of sub-maps. The pose state estimator may send to a second localizer a sub-map change message indicating the second sub-map.