Robotic Singulation via Pushing Heavy Items on Conveyor
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual singulation in parcel and distribution centers is labor-intensive and inefficient, and robotic singulation faces challenges due to cluttered mixes of items and dynamic workflows, making it difficult to identify, grasp, and separate items automatically.
Innovation Solution
A robotic singulation system that uses a vision system with sensors to detect and route items, determines a plan to handle items based on attributes like weight and size, and employs a robotic arm with a suction-based end effector to push or place items on a conveyor, adapting to changing conditions and avoiding collisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual singulation is used, then items can be separated and routed, but labor costs increase and throughput decreases
Solution Approach 1:
The system uses vision systems and sensors to automatically detect and identify items, with robotic arms autonomously performing singulation and routing without human intervention. The system self-regulates by monitoring item attributes and adjusting robotic actions in real-time
Solution Approach 2:
Manual mechanical singulation operations are replaced with an automated robotic system that uses vision systems for detection, sensors for measurement, and robotic arms with end effectors for physical manipulation and routing of items
2Extent of automation
If robotic singulation is implemented, then automation increases and labor costs decrease, but difficulty in identifying and grasping items in cluttered mixes increases
Solution Approach 1:
The vision system divides the cluttered scene into individual item segments, identifying boundaries and characteristics of each item separately. The system processes the cluttered mix by breaking down the complex visual data into manageable item-level information for robotic manipulation
Solution Approach 2:
The robotic system employs a universal end effector with multiple functions including grasping, pushing, and manipulating various item types. The vision and sensor systems serve multiple purposes: detection, identification, measurement, and routing decisions across diverse item categories
3Extent of automation
If robotic arms with end effectors are used, then automated grasping is achieved, but difficulty in adapting to changing states and conditions increases
Solution Approach 1:
The robotic system dynamically adjusts its operation by continuously monitoring item positions, orientations, and attributes through vision and sensors. The control system modifies robotic arm trajectories, end effector forces, and routing decisions in real-time based on detected changes in workspace conditions
Solution Approach 2:
The system implements closed-loop feedback by using vision systems and sensors to continuously detect item states and positions, comparing them against planned operations, and adjusting robotic actions accordingly. This feedback mechanism enables real-time adaptation to changing conditions during singulation and routing operations
4Productivity
If heavy items are handled by picking, then all items can be routed, but energy consumption increases and system reliability decreases
Solution Approach 1:
Instead of lifting heavy items vertically with the robotic arm, the system inverts the approach by using the conveyor belt's horizontal motion and pushing forces to transport heavy items. The robotic arm applies lateral pushing forces rather than vertical lifting forces, leveraging the conveyor's movement to achieve item transport
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 improves efficiency by autonomously sorting items with varying attributes, reducing labor costs and increasing throughput by accurately routing and placing items on a conveyor, even when they are heavy or require special handling.
Implementation Method 1
employs a robotic arm with a suction-based end effector to push or place items on a conveyor
Data Source
AI summary
The present application discloses a system, a method, and a computer system for moving items deemed to be too heavy to be picked up by a robotic arm. The method includes (i) receiving image data associated with a workspace, wherein the workspace includes a source of items to be placed singly each in a respective corresponding location on a segmented conveyance structure adjacent to at least a portion of the source of items, (ii) receiving an indication that a first item in the source of items is too heavy to be picked up by a first robotic arm the one or more processors are configured to control, (iii) determining, based at least in part on the image data, a plan to use the first robotic arm to push the first item onto an associated corresponding location on the segmented conveyance structure as the associated corresponding location on the segmented conveyance structure moves past the source of items, and (iv) controlling the first robotic arm to implement the plan.