Robotic Packing Pose Control With Force-Guided Reattempts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robotic packing systems struggle with efficiently packing objects into receptacles, particularly in real-world scenarios, due to their inability to handle non-rigid objects and unexpected errors, and they often require complex planning to avoid contact.
Innovation Solution
A computer-implemented method and system that uses imaging analysis to align the major axis of an object with the axis of a receiving space, and employs force feedback to iteratively adjust the object's pose during packing attempts, ensuring that contact forces do not exceed a predetermined threshold.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If the system avoids all contact during packing, then object damage is reduced, but packing robustness deteriorates when unexpected errors occur
Solution Approach 1:
The system dynamically changes the contact force parameter by establishing a threshold that allows controlled contact forces during packing operations. This enables the system to tolerate unexpected contacts without causing damage, while still maintaining robustness through force monitoring and corrective actions when thresholds are exceeded.
Solution Approach 2:
The system implements force feedback monitoring during packing operations. When contact forces exceed the predetermined threshold, the system detects this condition and initiates corrective actions, such as adjusting the robotic manipulator's pose or aborting the current packing attempt. This feedback mechanism provides robustness by enabling real-time responses to unexpected contacts while preventing object damage through controlled force levels.
2Object-affected harmful factors
If complex planning is used to avoid contact, then object damage is reduced, but system complexity increases
Solution Approach 1:
The system replaces complex mechanical planning and avoidance mechanisms with a simpler force sensing and feedback control approach. Instead of using sophisticated path planning algorithms to predict and avoid all potential contacts, the system uses force sensors to detect contacts in real-time and responds with simple corrective actions, significantly reducing computational and system complexity while maintaining object protection.
3Productivity
If alignment based on imaging analysis is used, then packing efficiency is improved, but measurement precision requirements increase
Solution Approach 1:
The system performs preliminary alignment of the object with the receptacle using imaging analysis to determine the object's major axis and calculate the appropriate pose before the packing operation begins. This preliminary action ensures that the object is properly oriented to minimize contact forces during insertion, improving packing efficiency while allowing the force feedback mechanism to handle any minor misalignments that occur during execution.
Data Source
AI summary
Controlling a Robotic Manipulator for Packing an Object Provided is a computer-implemented method of controlling a robotic manipulator for packing an object, involving obtaining an image of an object grasped by an end effector of the robotic manipulator and determining a major axis of the object in the image. A first object pose is determined wherein the major axis of the object is aligned with an axis of a receiving space. The robotic manipulator is controlled to manipulate the object to the first object pose above the receiving space and move the object from the first object pose down into the receiving space. In response to detecting by a force sensor a contact force above a predetermined force threshold at the end effector, the robotic manipulator is controlled to manipulate the object to a second object pose, above the receiving space, for initiating a further attempt to place the object in the receiving space.