Vehicle Position Estimation Using Graph Interpolation for Async Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous driving systems face challenges in accurately estimating vehicle position when asynchronous sensing data from different sensors with varying creation periods is not synchronized, leading to potential inaccuracies and latency in position information.
Innovation Solution
A method for modifying the graph structure by incorporating asynchronous sensing data using sensor data interpolation and graph node interpolation, allowing for the accurate and real-time estimation of vehicle position by aligning the data with a reference period.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If asynchronous sensing data is directly incorporated into the graph structure, then position estimation accuracy is improved, but computational complexity and processing time increase
Solution Approach 1:
The patent applies preliminary action by performing interpolation processing on asynchronous sensing data before incorporating it into the graph structure. The system predicts position information at reference time points using interpolation algorithms, which pre-processes the data to match the graph structure's temporal framework, thereby reducing computational complexity during real-time processing while maintaining accuracy
Solution Approach 2:
The patent changes parameters by transforming asynchronous sensing data into a synchronized format through interpolation. The system adjusts temporal parameters by predicting position information at specific reference time points, converting irregularly timed sensor data into a standardized temporal sequence that integrates seamlessly with the graph structure
2Measurement precision
If more nodes are added to the graph structure to accommodate asynchronous data, then data alignment accuracy is improved, but computation time increases
Solution Approach 1:
The patent applies partial action by selectively adding only the necessary minimum number of nodes to the graph structure. Instead of adding nodes for every possible data point, the system adds nodes only at reference time points where interpolation is needed, achieving sufficient data alignment without excessive computational overhead
Solution Approach 2:
The system performs preliminary interpolation calculations to determine exactly which nodes need to be added to the graph structure. By pre-calculating the required nodes based on the asynchronous data timestamps, the system avoids adding unnecessary nodes and optimizes the graph structure before actual position estimation processing
3Stability of the object's composition
If sensing data is synchronized to a reference period, then graph structure integration is improved, but real-time processing capability deteriorates
Solution Approach 1:
The patent applies periodic action by organizing the graph structure around reference time points with fixed periods. The system synchronizes sensing data to these periodic reference points through interpolation, creating a stable temporal framework that maintains graph structure consistency while enabling efficient batch processing at each periodic interval
Solution Approach 2:
The system performs preliminary interpolation to predict position information at reference time points before the actual graph processing occurs. This pre-computation aligns the asynchronous sensing data with the periodic graph structure in advance, reducing the processing burden during real-time execution and maintaining both consistency and speed
Data Source
AI summary
A method for position estimation of a vehicle based on a graph structure according to an exemplary embodiment of the present invention may include a sensing step of creating sensing data according to translation of the vehicle using a plurality of sensors; a graph structure creating step of creating a node according to a reference period and setting a constraint condition between the nodes to the sensing data synchronized with the reference period to create a graph structure; a graph structure modifying step of modifying the graph structure using the asynchronous sensing data when the asynchronous sensing data which is not synchronized with the reference period among the sensing data is input; and a position estimating step of creating position information of the vehicle using the graph structure.