Robot Gripper Posture Planning Using a Manipulability Map
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robotic handling systems face challenges in gripping objects of various shapes, sizes, and weights due to limitations in the range of possible postures and positions, particularly when using suction pads, which restrict access to restricted regions and limit the effectiveness of holding operations.
Innovation Solution
A handling device with a controller that generates holdable candidate points and determines holding postures using a manipulability map, which associates each position in the environment with the manipulability parameter calculated from joint angles, allowing for the selection of suitable postures and positions to enhance the accessibility and holding capabilities of the robot arm.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a robot hand is offset to access restricted regions, then accessibility to restricted regions is improved, but link length increases causing limitations in range of possible postures
Solution Approach 1:
The system dynamically selects from multiple pre-calculated holding plans based on real-time object detection results. The controller chooses the most appropriate holding plan that adapts to the specific object geometry and restricted region requirements, allowing the robot to achieve both accessibility and posture flexibility through dynamic plan selection rather than fixed mechanical configuration
Solution Approach 2:
The system changes operational parameters by selecting different holding plans with varying hand positions, postures, and suction pad configurations. Each holding plan contains pre-defined parameters for approach vectors, gripping forces, and joint angles that are optimized for specific object types and restricted region accesses, enabling parameter adaptation without physical reconfiguration
2Adaptability or versatility
If multiple holding plans are prepared in advance, then holding operations for various objects can be performed, but determination of the most appropriate holding plan becomes complex
Solution Approach 1:
The system uses detection results from object recognition (shape, size, weight, surface properties) as feedback to select the appropriate holding plan. The controller compares detected object characteristics against pre-stored holding plan criteria and automatically selects the best match, reducing complexity through rule-based decision making rather than exhaustive evaluation of all possible plans
Solution Approach 2:
Multiple holding plans are pre-calculated and stored in memory before operation, with each plan containing pre-determined parameters for specific object types and restricted regions. This preliminary preparation eliminates the need for complex real-time optimization, as the controller only needs to retrieve and execute the appropriate pre-planned solution based on object detection
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A handling device according to an embodiment has an arm, a holder, a storage, and a controller. The arm includes at least one joint. The holder is attached to the arm and is configured to hold an object. The storage stores a function map including at least one of information about holdable positions of the holder and information about possible postures of the holder. The detector is configured to detect information about the object. The controller is configured to generate holdable candidate points on the basis of the information detected by the detector, to search the function map for a position in an environment in which the object is present, the position being associated with the generated holdable candidate points, and to determine a holding posture of the holder on the basis of the searched position. The function map associates a manipulability with each position in the environment in which the object is present. The manipulability is a parameter calculated from at least one joint angle of the holder.