Robotic Object Pose Control for Stable Placement in Small Spaces
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated systems face challenges in handling and processing objects with low pose authority and low placement authority, such as floppy bags or cylindrical objects, which can fall or fall off conveyance systems during movement, especially when placing them into small spaces like cubbies or bags, particularly in e-commerce order fulfillment centers handling a wide variety of objects.
Innovation Solution
A method and system utilizing a programmable motion device with an end-effector that grasps objects, determines their pose using perception systems, adjusts the object's position for accurate placement, and places them in destination locations, ensuring stable orientation and positioning to prevent toppling and ensure efficient packaging and storage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated systems use standard conveyance and processing systems, then productivity is improved, but objects with low pose authority and low placement authority may fall over or fall off the system
Solution Approach 1:
The system determines the pose of objects while they are being grasped by the end-effector and calculates pose adjustments in advance before placement. This preliminary determination and adjustment calculation allows the system to pre-compensate for potential instability issues, ensuring objects are positioned correctly before being released onto the conveyance system.
Solution Approach 2:
The system uses pose-in-hand perception systems to continuously monitor and determine the actual pose of objects during grasping and placement operations. This feedback information is used to adjust placement strategies in real-time, allowing the system to adapt to objects with varying pose and placement authority characteristics and prevent falling or toppling during conveyance.
2Productivity
If objects are placed into small spaces like cubbies or bags, then packaging efficiency is improved, but the difficulty of detecting and measuring object pose increases
Solution Approach 1:
The system employs pose-in-hand perception systems as intermediary measurement devices that specifically capture object pose information while the object is still being held by the end-effector. This intermediary measurement approach occurs when the object is more accessible and easier to measure, before placement into constrained small spaces where measurement would be difficult.
Solution Approach 2:
The system performs pose determination and placement calculation in advance while the object is still accessible during grasping, before the object is placed into small destination spaces. This preliminary measurement and calculation avoids the measurement difficulties that would arise if attempted after placement into constrained spaces.
3Manufacturing precision
If human personnel pack objects by hand, then object placement accuracy is improved, but productivity decreases
Solution Approach 1:
The system replaces manual human packing operations with an automated robotic end-effector system controlled by computer vision and pose determination algorithms. The perception systems and control algorithms replicate and enhance human-like placement precision while operating at automated speeds, eliminating the productivity limitation of manual packing.
Solution Approach 2:
The system uses pose-in-hand perception to automatically determine object characteristics and self-adjust placement parameters without human intervention. The automated system serves itself by using its own sensing capabilities to guide precise placement, combining the accuracy previously requiring human judgment with automated speed.
Data Source
AI summary
A method of processing objects is disclosed. The method includes grasping an object with an end-effector of a programmable motion device, determining an estimated pose of the object as it is being grasped by the end-effector, determining a pose adjustment for repositioning the object for placement at a destination location in a destination pose, determining a pose adjustment to be applied to the object, and placing the object at the destination location in a destination pose in accordance with the pose adjustment.