Dynamic Factor-Graph Updates for Vehicle Surroundings Digital Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing graph-based SLAM methods generate inaccurate digital maps due to outdated data and failure to account for structural changes in the vehicle's surroundings.
Innovation Solution
A method that extends a basic factor graph with new data from subsequent trips, identifies changed nodes, and updates the digital map accordingly, using a computer-implemented approach to incorporate structural changes and improve map accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If graph-based SLAM methods are used to generate digital maps, then the mapping process can be automated, but the generated digital maps are inaccurate due to outdated data and failure to account for structural changes
Solution Approach 1:
The system dynamically updates the factor graph by comparing new sensor data with existing map data to identify and incorporate structural changes. This allows the mapping system to adapt to changes in the environment over time, resolving the contradiction between automation and accuracy by making the automated process dynamic rather than static.
Solution Approach 2:
The system implements a feedback mechanism where new sensor data from subsequent trips is continuously compared with the existing digital map, and changes are fed back into the factor graph for updating. This feedback loop ensures that the automated mapping process maintains accuracy by continuously correcting outdated information.
2Productivity
If a basic factor graph is created from previous trip data, then the initial digital map can be generated efficiently, but the map becomes outdated and inaccurate over time
Solution Approach 1:
The system performs preliminary actions by creating a basic factor graph from previous trip data to establish an initial digital map efficiently. This preliminary map serves as a foundation that can be quickly generated, while subsequent updates refine its accuracy without requiring complete regeneration.
Solution Approach 2:
The system maintains continuity by continuously updating the factor graph with new sensor data from subsequent trips. Rather than generating discrete, isolated maps, the system continuously refines the digital map by incorporating new information, ensuring both efficiency and currency of the map data.
3Measurement precision
If the entire factor graph is regenerated from new sensor data, then the digital map accuracy can be improved, but the computational complexity and time required increase significantly
Solution Approach 1:
The system segments the factor graph updating process by identifying only the specific nodes and factors that have changed compared to the basic factor graph. Instead of regenerating the entire factor graph, the system selectively updates only the affected portions, reducing computational complexity while maintaining accuracy.
Solution Approach 2:
The system applies partial action by performing only the necessary updates to the factor graph based on changes detected in new sensor data. Rather than completely regenerating the factor graph, the system applies minimal necessary changes to maintain accuracy, avoiding excessive computational effort.
4Ease of operation
If structural changes in the surroundings are not accounted for, then the mapping process remains simple, but the digital map becomes inaccurate in dynamic environments
Solution Approach 1:
The system detects parameter changes by comparing new sensor data with existing factor graph data to identify structural changes in the environment. When changes are detected, the system updates the relevant parameters in the factor graph, maintaining simplicity while adapting to dynamic environments through parameter adjustment rather than complete redesign.
Data Source
AI summary
A method for creating a digital map of surroundings of a vehicle, comprising: providing a basic factor graph, comprising nodes and factors that were created on the basis of single-trip data from a previous trip; providing further single-trip data relating to a further trip of a vehicle that is different from the previous trip; extending the basic factor graph by generating further nodes and further factors and inserting the further nodes and further factors into the basic factor graph on the basis of the provided further single-trip data, such that an extended factor graph is generated by extending the basic factor graph; identifying nodes of the further nodes which have changed by more than a specified deviation in comparison to the nodes of the provided basic factor graph; and creating a digital map on the basis of the extended factor graph in consideration of the identified nodes.

