Semantic Map Remapping via Feature Transformation Matrices

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing robotic mapping technologies face challenges in efficiently updating maps in dynamic environments, such as warehouses, where changes in space layout and feature positions occur frequently, leading to inaccuracies and increased manual effort in updating semantic labels.

Innovation Solution

A computing device determines a first and second map of an environment, identifying fixed and moved features, and applies transformations to assign semantic labels to the second map, ensuring accurate remapping and reducing manual intervention by automatically updating feature and label positions based on detected changes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual updating of semantic labels is used in dynamic environments, then accuracy of semantic labels can be maintained, but time consumption and labor effort increase significantly

Engineering Contradiction:

Improveaccuracy of semantic labelsVSAvoidtime consumption for updating maps

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs automatic remapping by identifying moved features, calculating transformations, and reassigning semantic labels without human intervention. The computing device autonomously detects feature movements, computes transformation matrices, and updates the map structure, enabling the system to service itself rather than requiring manual updating of semantic labels

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary identification of moved features and calculates transformations before the actual remapping process. By pre-processing the detection of feature movements and computing the necessary transformations in advance, the system prepares the data structure for efficient semantic label reassignment, reducing overall processing time

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If complete remapping is performed in dynamic environments, then map accuracy is improved, but processing time and computational resources increase

Engineering Contradiction:

Improvemap accuracyVSAvoidprocessing speed of map updates

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The remapping process is segmented into distinct phases: identifying moved features, calculating transformations for moved regions, and reassigning semantic labels. This segmentation allows the system to process only the affected portions of the map rather than performing complete remapping, thereby maintaining accuracy while improving processing efficiency

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs partial remapping by focusing only on regions containing moved features rather than processing the entire map. By applying transformations selectively to moved regions and their associated semantic labels, the system achieves sufficient map accuracy without the computational overhead of complete remapping

Inventive Principle:

Principle #16Partial or excessive action

3Ease of operation

If automated feature tracking is implemented in dynamic environments, then manual effort is reduced, but handling of moved features becomes more complex

Engineering Contradiction:

Improvemanual effort for map updatesVSAvoidcomplexity of transformation algorithms

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The system introduces an intermediary transformation calculation step that bridges feature detection and semantic label reassignment. By computing transformation matrices as an intermediate representation of feature movements, the system simplifies the overall process of handling moved features, making the automated tracking more manageable despite the inherent complexity

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS9574883B2Associating semantic location data with automated environment mapping

Publication Date: 2017.02.21 GDM HOLDING LLC

AI summary

Systems and methods are provided for generating maps with semantic labels. A computing device can determine a first map that includes features located at first positions and semantic labels located at semantic positions, and determine a second map that includes at least some of the features located at second positions. The computing device can identify a first region with fixed features located at first positions and corresponding equivalent second positions. The computing device can identify a second region with moved features located at first positions and corresponding non-equivalent second positions. The computing device can determine one or more transformations between first positions and second positions. The computing device can assign the semantic labels to the second map at second semantic positions, where the second semantic positions are the same in the first region, and where the second semantic positions in the second region are based on the transformation(s).