Multi-View Camera Motion Planning for Hidden Object Geometry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current motion planning systems for robots in warehousing and retail environments rely on limited image information, leading to inaccurate object structure estimation and unreliable interaction plans, especially when objects have hidden dimensions or complex geometries.
Innovation Solution
A computing system that uses multiple camera poses and viewpoints to generate 2D or 3D image information, allowing for accurate estimation of object structures by capturing additional views, such as side surfaces, and updating motion plans to ensure reliable robot-object interactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single camera pose is used for motion planning, then the system complexity is reduced, but the object structure estimation accuracy deteriorates due to hidden dimensions and limited viewpoints
Solution Approach 1:
The system transitions from a single 2D camera view to multiple 2D views that collectively provide 3D object structure information. By capturing images from different camera poses and combining them, the system reconstructs complete object geometry including hidden dimensions, effectively adding spatial dimensionality to the measurement process without requiring a complex 3D camera system
2Measurement precision
If multiple camera poses are used to capture complete object views, then the object structure estimation accuracy is improved, but the time required for motion planning increases
Solution Approach 1:
The system performs preliminary actions by capturing multiple images from different camera poses before motion planning begins. This pre-capture of comprehensive object structure data allows the subsequent motion planning to proceed with complete information, avoiding time-consuming adjustments during the planning phase itself
3Productivity
If limited image information is used, then the processing speed is maintained, but the reliability of motion planning deteriorates for objects with complex geometries
Solution Approach 1:
The system captures more image data than the minimum single view by acquiring multiple images from different poses. This excessive action of capturing redundant views from multiple angles provides comprehensive object structure information that ensures reliable motion planning for complex geometries, while the processing pipeline efficiently handles the additional data
Data Source
AI summary
A system and method for motion planning is presented. The system is configured, when an object is or has been in a camera field of view of a camera, to receive first image information that is generated when the camera has a first camera pose. The system is further configured to determine, based on the first image information, a first estimate of the object structure, and to identify, based on the first estimate of the object structure or based on the first image information, an object corner. The system is further configured to cause an end effector apparatus to move the camera to a second camera pose, and to receive second image information for representing the object's structure. The system is configured to determine a second estimate of the object's structure based on the second image information, and to generate a motion plan based on at least the second estimate.