Multi-Robot Singulation Planning for Conflict-Free Parcel Picking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual singulation processes in parcel and distribution centers are labor-intensive and inefficient due to the challenge of handling a cluttered mix of items of varying sizes, shapes, and orientations, making it difficult for robots to automate the separation and sorting of items for reliable machine reading and routing.
Innovation Solution
A robotic singulation system utilizing a robotic arm with a suction-based end effector, coordinated by a control computer with vision systems and sensors, to identify, grasp, and place items on a conveyor for sorting, while also employing human assistance through teleoperation when needed to maximize throughput and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple robots are deployed to perform singulation simultaneously, then productivity increases, but coordination complexity and conflict risk increase
Solution Approach 1:
The patent combines multiple robotic systems into a unified coordination framework where a central controller manages task allocation and conflict resolution. The controller merges information from multiple robots and integrates their actions to achieve coordinated singulation, transforming individual robot operations into a synchronized collective process that maximizes throughput while preventing conflicts.
Solution Approach 2:
The coordination system dynamically adjusts task assignments and robot behaviors based on real-time system state. The controller continuously monitors robot positions, item locations, and workflow conditions, adapting the coordination strategy to optimize productivity while avoiding conflicts. This dynamic approach allows the system to respond to changing conditions and maintain efficient operation.
2Extent of automation
If robots operate autonomously in dynamic item flow, then automation extent increases, but reliability of item identification and grasping decreases
Solution Approach 1:
The system employs continuous feedback loops where sensors monitor item flow, position, and characteristics in real-time. The control system uses this feedback to adjust robot actions, verify successful item identification and grasping, and correct errors. This feedback mechanism maintains high reliability in automated operation by constantly validating system state and responding to deviations.
Solution Approach 2:
The system performs preliminary actions such as pre-identifying items, pre-planning robot trajectories, and pre-coordinating task assignments before actual singulation occurs. This advance preparation ensures that when robots execute autonomous operations, they are working from validated plans that account for dynamic conditions, thereby maintaining reliability throughout the automated process.
3Ease of operation
If manual singulation is performed by human workers, then ease of operation is maintained, but productivity and labor efficiency deteriorate
Solution Approach 1:
The robotic system performs singulation autonomously without continuous human intervention. The robots self-coordinate through the centralized controller, self-adjust to dynamic conditions, and self-correct operational errors. This self-service capability eliminates the need for manual labor while maintaining operational effectiveness, thereby increasing productivity without sacrificing ease of system management.
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 robotic system enhances efficiency by automating the singulation process, reducing labor costs, and improving collective throughput by accurately sorting and routing items, even in complex and dynamic environments, while ensuring reliable machine-readable information capture.
Implementation Method 1
A robotic singulation system utilizing a robotic arm with a suction-based end effector
Data Source
AI summary
A robotic singulation system is disclosed. In various embodiments, sensor data including image data associated with a workspace is received. The sensor data is used to generate a three dimensional view of at least a portion of the workspace, the three dimensional view including boundaries of a plurality of items present in the workspace. A grasp strategy is determined for each of at least a subset of items, and for each grasp strategy a corresponding probability of grasp success is computed. The grasp strategies and corresponding probabilities of grasp success are used to determine and implement a plan to autonomously operate a robotic structure to pick one or more items from the workplace and place each item singly in a corresponding location in a singulation conveyance structure.