Underground SLAM Using Reduced Mapping Data for GNSS-Denied Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The lack of complementary technologies to Global Navigation Satellite Systems (GNSS) hinders the development of high-fidelity positioning and navigation in environments where line-of-sight satellite communications are unavailable, such as underground settings, posing challenges for industries like mining and tunneling that require precise positioning for safety and efficiency.
Innovation Solution
A system and method for simultaneous localization and mapping using inertial and mapping sensors, combined with machine learning models, to generate reduced mapping data and update local or global maps, providing accurate positioning and navigation in underground environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GNSS technology is used for positioning and navigation, then positioning accuracy is improved, but it becomes inapplicable in underground environments where line-of-sight satellite communications are unavailable
Solution Approach 1:
The system segments the positioning task into multiple components: inertial sensors provide short-term high-accuracy positioning, while mapping sensors capture environmental features. The mapping data is divided into reduced mapping data for efficient processing and correlation, enabling the system to function without satellite signals in underground environments.
Solution Approach 2:
The patent introduces mapping data and reduced mapping data as intermediary elements that enable positioning in GNSS-denied environments. These intermediaries serve as reference frameworks that allow the inertial navigation system to be localized and corrected without direct satellite communication, bridging the gap between inertial drift and environmental features.
2Measurement precision
If mapping data is processed in full detail, then mapping accuracy is improved, but computational complexity and processing time increase
Solution Approach 1:
The system extracts only the essential features from complete mapping data to create reduced mapping data. This extraction process removes redundant information while preserving critical spatial relationships and features needed for positioning, significantly reducing computational complexity while maintaining mapping accuracy.
Solution Approach 2:
The patent applies partial action by processing only the necessary portions of mapping data rather than analyzing every detail. The reduced mapping data contains just enough information for effective feature correlation and positioning, avoiding the excessive computational burden of processing complete high-fidelity mapping data in real-time.
3Reliability
If multiple sensors are integrated for simultaneous localization and mapping, then positioning reliability is improved, but system complexity increases
Solution Approach 1:
The system merges inertial sensors and mapping sensors into an integrated simultaneous localization and mapping framework. By combining these sensor types and their data streams, the system achieves enhanced positioning reliability through sensor fusion, where the strengths of each sensor type compensate for the weaknesses of the others.
Solution Approach 2:
The patent implements multi-functionality by using the same sensor system for multiple purposes: inertial sensors provide both orientation and position information, while mapping sensors simultaneously create environmental maps and provide features for localization. This universal approach reduces the need for separate dedicated systems.
4Productivity
If data reduction is applied to mapping data, then processing speed is improved, but information loss may occur
Solution Approach 1:
The reduced mapping data maintains local quality by preserving critical features and spatial relationships where they are most needed for positioning, while reducing detail in areas less critical for navigation. This selective preservation ensures processing speed improvement without significant information loss in the regions that matter most for localization.
Solution Approach 2:
The patent applies parameter changes by transforming mapping data from its original high-dimensional form into a reduced representation with optimized parameters. This transformation changes the data structure to be more computationally efficient while maintaining the essential geometric and spatial information needed for accurate positioning and mapping.
Data Source
AI summary
Systems and computer-implemented methods of simultaneous localization and mapping in underground environments are provided. The method comprises: generating mapping data of the underground environment and inertial measurement data of an agent traversing the underground environment; generating, by the agent, reduced mapping data by performing data reduction of the generated mapping data; updating, by the agent, a local map based on correlated features in the reduced mapping data; updating, by the agent, a localized position of the agent with reference to the updated local map; and providing, by the agent via a user interface, a localization and mapping output including at least one of the updated local map and the updated localized position of the agent.