Graph-Based State Data Fusion for Automated Vehicle Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated vehicle systems rely heavily on onboard sensor systems for localization, which can fail or degrade, leading to a loss of accuracy and availability in automated driving modes, especially when exchanging cooperative perception messages between vehicles.
Innovation Solution
A method for fusing state data from multiple mobile units using a control unit, where state data from one mobile unit is optimized by creating a time-position diagram and solving an optimization problem using algorithms like preconditioned conjugate gradient solvers, allowing for improved localization accuracy by integrating data from both onboard sensors and communication links.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If onboard sensor systems are used for localization, then localization function is available, but accuracy and reliability deteriorate when sensors fail or degrade
Solution Approach 1:
The patent combines data from multiple mobile units' sensor systems through data fusion to achieve more reliable and accurate localization. By merging measurements from multiple sources, the system maintains localization accuracy even when individual sensors fail or degrade.
Solution Approach 2:
The patent introduces communication links as intermediaries to transfer state data between mobile units. This mediator enables cross-validation and redundancy, allowing the system to maintain localization reliability and accuracy independent of single sensor failures.
2Measurement precision
If data from multiple mobile units is fused, then localization accuracy improves, but system complexity increases
Solution Approach 1:
The patent transforms the data fusion problem into an optimization problem by changing parameters to a time-position diagram representation. This parameter transformation simplifies the fusion process by providing a structured framework for combining data from multiple sources.
Solution Approach 2:
The patent replaces complex mechanical data fusion operations with mathematical optimization algorithms. By substituting iterative optimization methods for traditional fusion mechanisms, the system achieves accurate localization with reduced computational complexity.
3Measurement precision
If optimization problems are solved using iterative algorithms, then localization precision improves, but computational time increases
Solution Approach 1:
The patent performs preliminary organization of data into time-position diagrams and pre-processing of state data before optimization. This preliminary action structures the input data in a way that accelerates the optimization process while maintaining precision.
Solution Approach 2:
The patent changes the representation parameters to a time-position diagram format, which enables more efficient optimization algorithms. This parameter transformation reduces computational complexity while preserving localization precision.
Data Source
AI summary
A method for fusing state data via a control unit. State data of a first mobile unit and of an object ascertained via a sensor system of the first mobile unit are received. State data of an object ascertained via a sensor system of a second mobile unit and/or state data of the second mobile unit, transmitted via a communication link from the second mobile unit to the first mobile unit, are received. A node is created in a time-position diagram for each set of received state data of the first mobile unit, the second mobile unit, and the objects. A data optimization of the state data ascertained by the first mobile unit and/or by the second mobile unit is carried out. An optimization problem is created based on the optimized state data ascertained by the first mobile unit and the optimized state data received from the second mobile unit.