Pose Graph Updates Using Versioned Data for Incremental Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional map updating systems for autonomous and semi-autonomous machines require extensive data collection and computing resources, leading to outdated maps that are less reliable due to the need for batch rebuilds, which are time-consuming and inefficient.
Innovation Solution
Implement incremental map updates using versioned data to update specific portions of the map, leveraging pose graphs to ensure the most current data is used while considering older data, thereby reducing the need for extensive data collection and computing resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional batch rebuild processes are used to update maps, then map completeness is improved, but updating time and computing resource consumption increase significantly
Solution Approach 1:
The patent divides the map update process into segments by identifying and processing only the affected portions of the map based on changes in the pose graph, rather than performing complete batch rebuilds. This segmentation allows incremental updates that maintain map completeness while significantly reducing updating time and computational resources.
Solution Approach 2:
The system performs preliminary detection of pose graph changes before initiating map updates. By monitoring the pose graph for changes and identifying affected map portions in advance, the system prepares update targets beforehand, enabling efficient incremental updates without requiring complete batch processing.
2Reliability
If conventional batch rebuild processes are used to update maps, then map completeness is improved, but computing resource consumption increases significantly
Solution Approach 1:
The patent segments the map update computation by identifying only the specific map portions affected by pose graph changes. This selective processing approach maintains map completeness while dramatically reducing computing resource consumption compared to complete batch rebuilds that process the entire map regardless of changes.
Solution Approach 2:
The system performs partial action by updating only the necessary portions of the map rather than the entire map. This partial update approach is sufficient to maintain map completeness for affected areas while avoiding the excessive computing resource consumption of complete batch rebuilds.
3Measurement precision
If data collection machines navigate through the entirety of the environment to capture data, then map accuracy is improved, but navigation planning complexity and resource requirements increase
Solution Approach 1:
The patent segments the data collection requirement by identifying only the specific environment portions that correspond to detected pose graph changes. Data collection machines navigate only through these affected portions rather than the entire environment, maintaining map accuracy for changed areas while reducing navigation planning complexity.
Solution Approach 2:
The system performs preliminary identification of affected map portions and corresponding environment areas before dispatching data collection machines. This preliminary action enables targeted navigation planning that captures necessary data for maintaining map accuracy without requiring comprehensive environment coverage.
Data Source
AI summary
In various examples, updating pose graphs using versioned data for autonomous and/or semi-autonomous systems and applications is described herein. Systems and methods herein may generate and/or update a pose graph (e.g., a pose map) associated with an environment, where the pose graph indicates poses associated with data (e.g., the machines when generating the data) used to generate a map. For instance, amounts of coverage associated with first poses may be determined using both a first version of data associated with the first poses and a second version of data, where an amount of coverage may indicate how well the second version of data represents a same area of the environment as compared to the first version of data. The amounts of coverage may then be used to remove one or more of the first poses that include sufficient coverage from the pose graph.