Robotic Pick Verification Using Vision and Weight Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current object processing systems face inefficiencies and errors in handling objects of varying sizes and weights due to potential mislabeling and incorrect information, leading to errors in sorting and processing, and require more efficient and cost-effective solutions for accurate routing and placement.
Innovation Solution
An object processing system incorporating a programmable motion device with an end-effector and a perception system that includes weight sensing conveyors and camera systems to detect and correct for errors in object handling, ensuring accurate grasping, movement, and placement of objects into destination containers, while monitoring for dropped or displaced objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If automated systems retrieve and sort objects in arrival order using heuristics, then sorting can be performed with simple rules, but a large number of collection bins are required when the number of different types of input objects is large
Solution Approach 1:
The system dynamically adjusts the sorting approach by allowing objects to be held in temporary storage and re-sorted based on destination requirements rather than following a fixed arrival-order heuristic. This dynamic reconfiguration enables fewer collection bins to handle a larger variety of object types.
Solution Approach 2:
The system introduces a time dimension to the sorting process by allowing objects to wait in temporary storage and be sorted in a different sequence than their arrival order. This enables the system to group objects by destination rather than by arrival time, reducing the number of bins needed.
2Extent of automation
If robotic systems grasp and move objects from one location to another, then automation of object handling is achieved, but errors such as picking multiple objects, picking objects below others, or dropping objects may occur
Solution Approach 1:
The system performs preliminary verification by capturing images of objects before the robotic gripper engages and compares them with the intended target. This preliminary check prevents incorrect object selection and ensures the gripper is positioned correctly before attempting to grasp the object.
Solution Approach 2:
The system uses vision feedback to continuously monitor the robotic system's actions, verifying that the correct object is selected and successfully transferred. If an error is detected (such as picking the wrong object or failing to pick), the system can correct the error by retrieving the correct object from the source container.
3Reliability
If weight sensing conveyors are used to detect dropped objects, then object loss can be detected, but the system complexity increases
Solution Approach 1:
The vision system serves multiple functions: it identifies objects for the robotic gripper, verifies correct object selection, detects dropped objects, and provides feedback for error correction. This multi-functionality reduces the need for separate detection systems while maintaining comprehensive monitoring capabilities.
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 system ensures accurate and reliable processing of objects by maintaining knowledge of object locations and weights, minimizing errors and improving efficiency in sorting and routing, thereby enhancing the overall processing speed and reducing costs.
Implementation Method 1
an input area including a weight sensing conveyor section and the plurality of objects being provided within at least one input container
Data Source
AI summary
An object processing system including an input area for receiving a plurality of objects to be processed, an output area including a plurality of destination containers for receiving any of the plurality of objects, a programmable motion device proximate the input area and the output area, the programmable motion device including an end-effector for grasping a selected object of the plurality of objects, and a perception system for detecting the unexpected appearance of any of the plurality of objects that is not associated with the end-effector of the programmable motion device.