3D Camera Distance Calculation for Robot Occlusion Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for calculating the minimum distance between industrial robots and dynamic objects in their workspace are either computationally intensive or prone to errors due to occlusion issues, particularly with single-camera depth space approaches and multi-sensor techniques that require precise calibration.
Innovation Solution
A method using images from one or more three-dimensional cameras to detect object edges, subtract the robot and background, overlay depth values, and calculate distances only between object edge pixels and robot control points, with multiple cameras used to resolve occlusion by computing independent minimum distances and selecting the maximum result, which does not significantly increase computational load and eliminates the need for inter-camera calibration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If point cloud-based distance calculation is used, then measurement precision is improved, but computational complexity increases significantly
Solution Approach 1:
The patent extracts only the essential information needed for distance calculation by detecting object edges and identifying control points on the robot, rather than processing all points in the point cloud. This selective extraction of critical geometric features dramatically reduces computational complexity while maintaining distance calculation accuracy.
Solution Approach 2:
The patent segments the object into its edge轮廓 (contour) and the robot into discrete control points, breaking down the complex full-point cloud processing into manageable components. This segmentation allows for efficient pairwise distance calculation between edge pixels and control points without the computational burden of processing all point cloud data.
2Device complexity
If single-camera depth space approach is used, then computational complexity is reduced, but measurement precision deteriorates due to occlusion
Solution Approach 1:
The patent introduces multiple cameras as intermediary observation points to resolve occlusion issues. By capturing images from different viewpoints, the system can identify control points that are not occluded from any single camera perspective, thereby improving measurement precision without requiring complex multi-sensor fusion algorithms.
Solution Approach 2:
The patent uses multiple cameras to capture more information than a single camera would provide, deliberately acquiring excessive visual data from multiple perspectives. This partial redundancy allows the system to select the best unoccluded control points for distance calculation, improving accuracy while keeping computational complexity manageable through selective processing.
3Measurement precision
If multi-sensor technique is used to resolve occlusion, then measurement precision is improved, but device complexity and calibration requirements increase
Solution Approach 1:
The patent makes the camera system multi-functional by using the same camera(s) for both object detection and depth measurement through edge detection algorithms. This universal approach eliminates the need for separate depth sensors and their associated calibration procedures, reducing device complexity while maintaining measurement precision through computational geometry methods.
Data Source
AI summary
A method and system for calculating a minimum distance from a robot to dynamic objects in a robot workspace. The method uses images from one or more three-dimensional cameras, where edges of objects are detected in each image, and the robot and the background are subtracted from the resultant image, leaving only object edge pixels. Depth values are then overlaid on the object edge pixels, and distance calculations are performed only between the edge pixels and control points on the robot arms. Two or more cameras may be used to resolve object occlusion, where each camera's minimum distance is computed independently and the maximum of the cameras' minimum distances is used as the actual result. The use of multiple cameras does not significantly increase computational load, and does require calibration of the cameras with respect to each other.