SLAM Positioning via Moving Object Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional SLAM techniques face precision issues due to movable or moving objects in the environment, leading to uncertainties and misjudgments in map construction and positioning.
Innovation Solution
A method that continuously detects the surrounding environment, classifies objects as moving or static, filters out moving object information, and uses a SLAM algorithm for precise positioning based on filtered data, enhancing the accuracy of target object placement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional SLAM techniques use sensors to detect surrounding environment and construct maps, then positioning functionality is achieved, but positioning precision deteriorates due to moving objects causing uncertainty and misjudgments
Solution Approach 1:
The patent extracts and removes moving object information from the detection data before feeding it to the SLAM algorithm. By identifying objects that change position between time points and excluding their data, the system prevents moving objects from causing uncertainty and misjudgments in map construction, thereby improving positioning precision while maintaining reliable mapping
Solution Approach 2:
The patent performs preliminary classification of detected objects as moving or static before the SLAM processing stage. By pre-identifying and filtering out moving objects in advance, the system ensures that only reliable static object data is used for map construction and positioning, resolving the contradiction between achieving positioning functionality and maintaining precision
Data Source
AI summary
A method of simultaneous localization and mapping (SLAM) is provided to position a target object. Each of detected tracked objects in a surrounding environment of the target object is classified into a moving object or a static object based on data detected at different time points. The target object is then positioned without considering any of the tracked objects that are classified into a moving object.