Robot Sub-Map Anchoring for Memory-Efficient Occupancy Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing Simultaneous Localization and Mapping (SLAM) techniques face challenges in efficiently creating an occupancy map without storage requirements growing linearly with time, as all sensor readings and their associated poses need to be stored for re-processing, leading to increased memory demands.
Innovation Solution
A system and method where a robot generates parameter data maps by creating new grids associated with anchor nodes when pose uncertainty exceeds a threshold, allowing for the merging of local grids into a comprehensive map in a global reference frame, thereby limiting memory requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all sensor readings and their associated poses are stored to allow re-processing when new information arrives, then map accuracy improves over time, but storage requirements grow linearly with time
Solution Approach 1:
The patent divides the mapping process into multiple independent sub-maps, each associated with a key pose. Instead of storing all sensor readings in a single growing data structure, the system segments the environment map into discrete sub-maps that can be independently stored and processed. Each sub-map contains only the sensor readings relevant to its associated key pose, preventing linear growth of total storage requirements.
Solution Approach 2:
The system changes the parameter of data retention by storing only essential map data in sub-maps rather than preserving all intermediate sensor readings. When a new key pose is identified, the system creates a new sub-map with selective data from sensor readings, transforming the storage approach from comprehensive retention to selective preservation based on pose significance.
2Measurement precision
If all sensor readings are stored for re-processing, then the estimate of robot trajectory improves, but memory requirements increase linearly with time
Solution Approach 1:
The patent segments the robot trajectory estimation into multiple independent sub-estimations, each associated with a key pose and its corresponding sub-map. By dividing the continuous trajectory into discrete segments anchored at key poses, the system can improve trajectory accuracy through repeated refinement of individual segments without requiring proportional increases in total memory storage.
Solution Approach 2:
The system extracts only the essential data needed for trajectory estimation by creating sub-maps that contain selective sensor readings associated with key poses. Rather than retaining all sensor readings, the extraction process identifies and preserves only those readings critical for trajectory refinement, reducing memory requirements while maintaining estimation accuracy.
3Quantity of substance
If sub-maps are created for each key pose, then storage requirements are limited, but the complexity of merging sub-maps into a global map increases
Solution Approach 1:
The patent introduces key poses as intermediary elements that mediate between individual sensor readings and the global map. Each key pose serves as a reference point that anchors a sub-map and provides a transformation basis for merging. This intermediary structure simplifies the merging process by establishing clear reference frames and transformation relationships, reducing the overall complexity of integrating multiple sub-maps into a coherent global map.
Data Source
AI summary
A system and method for mapping parameter data acquired by a robot mapping system is disclosed. Parameter data characterizing the environment is collected while the robot localizes itself within the environment using landmarks. Parameter data is recorded in a plurality of local grids, i.e., sub-maps associated with the robot position and orientation when the data was collected. The robot is configured to generate new grids or reuse existing grids depending on the robot's current pose, the pose associated with other grids, and the uncertainty of these relative pose estimates. The pose estimates associated with the grids are updated over time as the robot refines its estimates of the locations of landmarks from which determines its pose in the environment. Occupancy maps or other global parameter maps may be generated by rendering local grids into a comprehensive map indicating the parameter data in a global reference frame extending the dimensions of the environment.