3D Pose Determination Using Encoded Target Markers for Robotic Gripping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining the three-dimensional pose of an object require prior knowledge of the object's geometry and gripping poses, leading to increased setup effort when dealing with multiple non-identical components.
Innovation Solution
A method using a target marker with encoding modules that provide object and gripping parameters, allowing for the determination of the three-dimensional pose without prior teaching, by encoding specific information such as size, gripping pose, and gripper geometry directly onto the marker.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If target markers with simple geometric shapes are used for pose determination, then the detection process is straightforward, but the setup effort increases with growing number of non-identical components due to object-specific gripping poses that must be taught in
Solution Approach 1:
The target marker encodes object-specific gripping poses and parameters in advance during marker creation. This preliminary encoding eliminates the need for time-consuming teaching processes for each new object type, as the robot system can directly read the gripping parameters from the marker itself.
Solution Approach 2:
The target marker serves itself by containing all necessary information about the object it is attached to, including gripping poses and object parameters. The marker provides this information autonomously to the robot system without requiring external databases or manual programming, enabling the system to adapt to new objects immediately.
2Reliability
If object-specific gripping poses are taught in for each component, then accurate gripping is achieved, but the setup effort increases with growing number of non-identical components
Solution Approach 1:
The target marker serves multiple functions: it provides pose information for detection, encodes object-specific gripping poses, and stores object parameters. This multi-functionality allows a single marker design to handle diverse objects without requiring separate teaching processes, reducing setup complexity while maintaining gripping accuracy.
Solution Approach 2:
The system transitions from fixed, pre-programmed gripping parameters to dynamic parameters encoded on each target marker. This allows the gripping pose and other parameters to change adaptively based on the specific object being handled, enabling accurate gripping of non-identical components without increasing setup complexity.
3Productivity
If prior knowledge of object geometry is required for pose determination, then the determination process is simplified, but the system cannot handle new or varying object types without reconfiguration
Solution Approach 1:
The system adds an information dimension to the traditional target marker by encoding object parameters and gripping poses within the marker structure itself. This transforms the marker from a simple geometric reference into an information-carrying device that provides both pose information and object-specific parameters, enabling fast and adaptable pose determination.
Solution Approach 2:
The target marker acts as an intermediary between the robot system and the object. It carries and transmits all necessary information about the object, including geometry and gripping parameters, allowing the robot system to determine pose and plan gripping actions without requiring prior knowledge or reconfiguration for new object types.
Data Source
AI summary
A target marker (1) for determining a three-dimensional pose of an object (4) has a predetermined number of encoding modules (2). The encoding modules (2) of the target marker (1) are present in a defined module pattern (10) that encodes a character string that includes specific information that defines object parameters of the object (4), selected from the group comprising at least a size of the target marker (1) and/or gripping parameters for gripping the predetermined object (4) from the group comprising at least a gripping pose of a gripper, a gripper geometry, and gripper forces.