Vehicle Localization via Multi-Vehicle Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle localization systems are prone to errors due to inaccurate data from sensors, which can affect the accuracy of vehicle location and orientation determination, especially in autonomous vehicle operations where precise navigation is critical.
Innovation Solution
A computer system that determines the localization of a vehicle by wirelessly receiving data from other vehicles with overlapping fields of view, calculating pair-wise localizations relative to a global coordinate system, and adjusting the localization to minimize distances between multiple vehicle perspectives, using sensor data from GPS, LIDAR, camera, or visual odometer sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If vehicle localization is determined based on single vehicle sensor data, then the system complexity is low, but the localization accuracy is poor due to sensor errors
Solution Approach 1:
The patent combines sensor data from multiple vehicles to determine localization. The system receives sensor data from the ego-vehicle and neighboring vehicles, then integrates this multi-source data through processing modules to compute a consensus localization that is more accurate than any single vehicle's sensor data alone.
Solution Approach 2:
The patent introduces a wireless communication system as an intermediary to transmit sensor data between vehicles. This intermediary enables the sharing and integration of localization data from multiple vehicles without requiring direct physical coupling between them.
2Measurement precision
If data from multiple vehicles is integrated, then localization accuracy improves, but the processing complexity increases
Solution Approach 1:
The patent segments the localization determination into distinct processing modules: a data reception module that collects sensor data from multiple vehicles, a processing module that integrates and reconciles the data, and an output module that generates the final localization. This segmentation manages complexity by organizing the integration process into manageable stages.
Solution Approach 2:
The system uses feedback mechanisms to iteratively refine localization estimates by comparing sensor data from multiple vehicles and adjusting the consensus localization based on discrepancies. This feedback loop continues until convergence, improving accuracy while managing processing complexity through iterative refinement.
Data Source
AI summary
A computer is programmed to determine a localization of a first vehicle, including location coordinates and an orientation of the first vehicle, based on first vehicle sensor data, and to wirelessly receive localizations of respective second vehicles, wherein a first vehicle field of view at least partially overlaps respective fields of view of each of the second vehicles. The computer is programmed to determine pair-wise localizations for respective pairs of the first vehicle and one of the second vehicles, wherein each of the pair-wise localizations defines a localization of the first vehicle relative to a global coordinate system based on a (a) relative localization of the first vehicle with reference to the respective second vehicle and (b) a second vehicle localization relative to the global coordinate system, and to determine an adjusted localization for the first vehicle that has a minimized sum of distances to the pair-wise localizations.