Suction Gripper Uncertainty Classification for Safe Grasping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robotic manipulators face challenges in securely grasping objects with unknown or uncertain extents and poses, which can lead to damage of the object or surrounding objects due to improper force application.
Innovation Solution
A method for a suction-based gripper of a mobile robot that involves receiving perception information, determining uncertainty information about the object's extent and pose, and using this information to determine a grasp strategy, which includes classifying suction cups and controlling their activation to achieve a secure grasp.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the robotic manipulator approaches the object with high speed to improve productivity, then the efficiency of pick-and-place operations is improved, but the risk of damaging the object or other objects increases due to uncertain extent and pose
Solution Approach 1:
The system performs preliminary classification of suction cups into confident and unconfident subsets based on predicted contact confidence before the grasping action. This preliminary categorization allows the robot to prepare appropriate control strategies in advance, enabling faster and safer operation by pre-planning which suction cups to activate and how to apply force, thus resolving the contradiction between speed and safety.
Solution Approach 2:
The system dynamically adjusts the grasping strategy based on real-time uncertainty information. By classifying suction cups according to their predicted contact confidence and adapting the activation sequence accordingly, the system creates a dynamic control approach that can respond to uncertain object properties, allowing high-speed operation while maintaining safety through adaptive force application.
2Object-affected harmful factors
If the robotic manipulator uses a conservative approach with low approach speed to avoid damage, then the safety of the object is improved, but the productivity of the system decreases
Solution Approach 1:
The system applies different control qualities to different regions of the gripper by classifying suction cups into confident and unconfident subsets. Confident suction cups (those likely to contact the object) are activated with appropriate force, while unconfident suction cups are handled more cautiously or activated later. This localized differentiation of control strategy allows the system to maintain safety while improving overall productivity by not being uniformly conservative.
3Measurement precision
If the perception system collects more data to reduce uncertainty about object extent and pose, then the measurement precision is improved, but the time required for perception increases, reducing productivity
Solution Approach 1:
The system performs partial perception by collecting only the essential data needed to classify suction cups into confident and unconfident subsets, rather than attempting to fully characterize the object. This partial action approach provides sufficient information for safe and effective grasping without the time cost of complete object characterization, thus resolving the contradiction between measurement precision and perception time.
4Reliability
If the system activates all suction cups simultaneously to ensure secure grasp, then the reliability of grasping is improved, but the force control becomes less precise, increasing the risk of object damage
Solution Approach 1:
The system employs periodic or staged activation of suction cups based on their classification. Instead of simultaneous activation, suction cups are activated in sequences or stages - first the confident subset, then potentially the unconfident subset if needed. This periodic activation pattern ensures reliable grasping while controlling force application to prevent object damage, resolving the contradiction between grasp security and force control precision.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The method enables the robot to approach and grasp objects securely, even with uncertain dimensions, reducing the risk of damage to the object or other objects, and improving the efficiency of pick-and-place operations.
Implementation Method 1
An on-board vacuum system may then be activated to use suction to adhere the object to the gripper.
Data Source
AI summary
Methods and apparatus for grasping an object by a suction-based gripper of a mobile robot are provided. The method comprises receiving, by a computing device, from a perception system of the mobile robot, perception information reflecting an object to be grasped by the suction-based gripper, determining, by the computing device, uncertainty information reflecting an unknown or uncertain extent and/or pose of the object, determining, by the computing device, a grasp strategy to grasp the object based, at least in part, on the uncertainty information, and controlling, by the computing device, the mobile robot to grasp the object using the grasp strategy.