Electronic Map Updating for Autonomous Vehicle Navigation Changes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Self-driving material-transport vehicles face challenges in maintaining an accurate electronic map of their environment, as the map becomes outdated due to changes in the surroundings, leading to inefficiencies and potential navigation issues.
Innovation Solution
A method and system for updating the electronic map by collecting image data at a self-driving material-transport vehicle's current position, comparing it with stored data to determine dissimilarity levels, and updating the map accordingly, including replacing or adding map nodes based on these comparisons to ensure the map reflects the current environment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the electronic map is continuously updated to maintain accuracy, then the map accuracy improves, but the computational complexity and processing time increase
Solution Approach 1:
The system updates only specific portions of the electronic map (local areas) rather than the entire map. When a vehicle traverses a region, only the map nodes in that region are updated by comparing sensor data with stored map data, leaving other regions unchanged. This localized update approach maintains map accuracy in traversed areas while avoiding the computational burden of updating the entire map.
Solution Approach 2:
The system performs partial updates by comparing sensor data only with relevant map nodes in the current vehicle position and neighboring nodes. The dissimilarity comparison is performed selectively on portions of the map that are likely to have changed, rather than exhaustively checking the entire map. This partial action approach achieves sufficient map accuracy while reducing computational complexity.
2Measurement precision
If the electronic map is continuously updated to reflect environmental changes, then the map accuracy improves, but the time required for updates increases
Solution Approach 1:
The electronic map is updated periodically as vehicles traverse different regions, rather than continuously in real-time. The system accumulates sensor data during vehicle operation and performs map updates at intervals when vehicles pass through areas of interest. This periodic update strategy maintains map accuracy over time while minimizing the time spent on update operations.
Solution Approach 2:
Updates are performed locally in the regions where vehicles are currently operating, rather than globally across the entire map. The system identifies map nodes within the vehicle's current position and neighboring nodes, and updates only those specific portions. This localized approach reduces update time by avoiding unnecessary processing of distant map areas that are unlikely to have changed.
3Measurement precision
If the electronic map includes detailed information about all areas, then the map accuracy improves, but the map size and storage requirements increase
Solution Approach 1:
The electronic map is divided into discrete map nodes, each representing a specific location with associated sensor data. Rather than storing continuous detailed information about entire regions, the map is segmented into individual nodes that can be independently stored and updated. This segmentation allows the system to maintain detailed information only at specific key locations while using less overall storage space.
Solution Approach 2:
The system stores detailed sensor data only at map nodes corresponding to actual vehicle positions and neighboring nodes, rather than uniformly across the entire map area. Areas that have not been traversed or are unlikely to change maintain simpler representations. This local quality approach ensures high accuracy in frequently visited areas while reducing overall map size.
Data Source
AI summary
Systems and methods for updating an electronic map of a facility are disclosed. The electronic map includes a set of map nodes. Each map node has a stored image data associated with a position within the facility. The method includes collecting image data at a current position of a self-driving material-transport vehicle; searching the electronic map for at least one of a map node associated with the current position and one or more neighboring map nodes within a neighbor threshold to the current position; comparing the collected image data with the stored image data of the at least one of the map node and the one or more neighboring map nodes to determine a dissimilarity level. The electronic map may be updated based at least on the collected image data and the dissimilarity level. The image data represents one or more features observable from the current position.