Mobile Object Route Control Using 3D Light Noise Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional technologies fail to accurately recognize and remove light source noise from candidate obstacles, leading to misinterpretation of travel routes for mobile objects.
Innovation Solution
A mobile object control device and method that utilizes a hardware processor to analyze point group distributions and recognize light source noise by identifying maximum points in a height direction, allowing for accurate removal of such noise through clustering and filtering.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional obstacle recognition methods are used, then candidate obstacles are identified based on LIDAR corresponding points projected onto horizontal plane grid cells, but light source noise cannot be properly recognized and removed
Solution Approach 1:
The patent transitions from two-dimensional horizontal plane grid cell analysis to three-dimensional point cloud analysis by examining the height direction distribution of corresponding points. This dimensional expansion enables the system to distinguish light source noise from actual obstacles based on vertical position characteristics, thereby improving noise recognition accuracy while maintaining obstacle identification reliability
Solution Approach 2:
The patent applies different analysis methods to different spatial regions by performing noise determination processing on point groups within predetermined areas around the mobile object. By analyzing the local height distribution characteristics of corresponding points in specific regions, the system can effectively identify and remove light source noise while preserving accurate obstacle detection in other areas
Data Source
AI summary
A mobile object control device includes a recognizer configured to recognize a point group corresponding to an object present around the mobile object based on an image of surrounding situations of a mobile object, and a controller configured to determine a moving route of the mobile object based on the surrounding situations and control the mobile object so that the object moves along the determined moving route, in which the recognizer calculates a distribution in a height direction of a point group recognized as a candidate for the object in a predetermined area around the mobile object, and executes noise determination processing for determining whether light source noise is included in a point group in the predetermined area based on the distribution.