Crowdsourced 3D Point Cloud Mapping for Multi-Device Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current robotic navigation systems are ill-equipped to handle multiple data streams and leverage crowd-sourced information effectively for creating and managing three-dimensional spatial models, limiting their ability to navigate complex environments efficiently.
Innovation Solution
A system that generates and merges three-dimensional point cloud maps from crowd-sourced data, identifies virtual landmarks, and associates physical locations with these maps to provide accurate navigation and localization, enabling devices to share and reuse these maps for improved navigation across various devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If individual robots create their own three-dimensional maps using sensor data, then each robot can navigate its local environment, but the system cannot effectively handle multiple data streams or leverage crowd-sourced information from multiple devices
Solution Approach 1:
The patent merges three-dimensional point cloud maps from multiple independent devices into a unified crowd-sourced map. The system receives map data from multiple devices, identifies overlapping regions through coordinate transformation and spatial analysis, and combines these maps into a comprehensive environmental model that leverages crowd-sourced information while managing data stream complexity centrally.
2Reliability
If the system merges multiple three-dimensional point cloud maps from different devices, then a comprehensive global map is created, but the process of determining overlaps and merging maps increases computational complexity
Solution Approach 1:
The patent segments the map merging process into distinct modular steps: receiving individual device maps, transforming coordinates to a common reference frame, identifying overlapping regions through spatial analysis, and combining maps in the overlap areas. This segmentation reduces computational complexity by breaking down the complex merging task into manageable sub-tasks that can be processed systematically.
Solution Approach 2:
The system introduces a central server as an intermediary that manages the coordinate transformation and map merging processes. The server acts as a mediator between multiple devices, receiving their individual maps, performing the computationally intensive overlap detection and merging operations, and distributing the consolidated global map back to devices, thereby simplifying the architecture and managing computational load centrally.
3Measurement precision
If virtual landmarks are identified and associated with physical locations for localization, then accurate device positioning is achieved, but the process of associating coordinates and calibrating devices adds operational complexity
Solution Approach 1:
The patent implements self-service calibration where devices automatically perform calibration movements along axes within three-dimensional space to align their captured maps with the global map. The system autonomously identifies virtual landmarks, associates their coordinates with physical locations, and adjusts device parameters without requiring manual intervention, thereby achieving accurate localization while simplifying operations.
Data Source
AI summary
Described is a system for leveraging crowd sourced data for mapping and navigation within a spatial environment. The system may merge various map fragments received from multiple devices to create a global 3D point cloud map. The system may also provide the ability to identify real-world virtual landmarks in an environment and associate these virtual coordinates with locations within the 3D point cloud map. These virtual landmarks may then be used to reference and index objects detected within the environment. Accordingly, these virtual landmarks and objects may then be used for mapping and navigation. For example, the objects may be referenced by various devices in real time for re-localization, and the virtual landmarks maybe used by various devices to triangulate accurate positions. Accordingly, described is an efficient mechanism for leveraging crowd sourced data to improve navigation within a spatial environment.