Salient-Object SLAM for Faster Robot Localization and Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robots face challenges in accurately determining their position and mapping their environment for autonomous navigation due to the need for precise and easily searchable map information, which existing methods do not adequately address.
Innovation Solution
A method involving a robot or cloud server that stores image information and extracts salient objects from images to generate maps, using camera sensors to capture images, detect objects, select salient objects, and store their coordinate information for improved localization and mapping accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the robot stores and processes complete image information for SLAM, then the accuracy of location estimation is improved, but the computational complexity and processing time increase
Solution Approach 1:
The patent extracts salient objects from complete image information and stores only these key features along with their coordinate data. This extraction process reduces the data volume significantly while maintaining the essential information needed for accurate location estimation, thereby resolving the contradiction between accuracy and computational complexity
Solution Approach 2:
Instead of storing and processing complete images, the system creates simplified copies representing salient objects and their positions. These copied features serve as sufficient proxies for the original images, enabling accurate SLAM with reduced computational burden
2Reliability
If the robot stores detailed map information for accurate position identification, then the reliability of navigation is improved, but the storage requirements and data processing time increase
Solution Approach 1:
The system extracts only the essential salient objects and their coordinate information from complete map data, storing these key features instead of full images. This extraction maintains navigation reliability by preserving critical positional references while significantly reducing storage requirements and processing time
3Measurement precision
If the robot uses traditional SLAM methods with complete image data, then comprehensive environmental mapping is achieved, but the speed of location estimation decreases
Solution Approach 1:
The patent extracts salient objects from complete image data and stores only these key features with their coordinate information. This extraction maintains comprehensive environmental mapping by preserving essential spatial references while dramatically improving location estimation speed through reduced data processing requirements
Data Source
AI summary
The present disclosure relates to a method for performing simultaneous localization and mapping (SLAM) with respect to a salient object in an image, a robot and a cloud server for implementing such method. According to an embodiment of the present disclosure, a robot includes a camera sensor configured to capture one or more images for the robot to perform the SLAM with respect to a salient object for estimating a location of the robot within the space, a map storage configured to store the information for the robot to perform the SLAM, and a controller that is configured to: detect an object from the captured image; select, as a specific salient object for identifying the space, the detected object verified as corresponding to the specific salient object; and store, in the map storage, the selected specific salient object and coordinate information related to the selected specific salient object.