Sensor-Guided Robotic Singulation for Dynamic Mixed-Item Workcells
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual singulation processes in parcel and distribution centers are labor-intensive and inefficient, and the use of robots to perform singulation is challenging due to the cluttered mix of items and dynamic flow at workstations.
Innovation Solution
A robotic singulation system that uses data associated with the workspace or items to determine a plan for singulation, including identifying attributes such as weight, size, and type of packaging, and dynamically updating paths or trajectories based on sensor data and context.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual singulation is used, then flexibility and adaptability to item attributes are maintained, but labor intensity increases and throughput decreases
Solution Approach 1:
The robotic system autonomously identifies item attributes using sensors, plans singulation trajectories, and executes placement without continuous human intervention. The system serves itself by automatically adapting to varying item characteristics through real-time sensor data processing and dynamic path planning.
Solution Approach 2:
Manual mechanical sorting by human workers is replaced with an automated robotic system that uses sensors, computer vision, and automated planning algorithms to identify items and determine placement locations, substituting human cognitive and physical processes with automated systems.
2Productivity
If robotic singulation is implemented, then labor costs are reduced and throughput increases, but difficulty in identifying and grasping items in cluttered mixes increases
Solution Approach 1:
The system performs preliminary sensing and identification of item attributes before grasping and placement. Sensors scan and characterize items in the cluttered mix ahead of time, allowing the planning system to pre-calculate trajectories and grasp strategies, thereby reducing the difficulty of real-time detection and measurement during execution.
Solution Approach 2:
The system transitions from two-dimensional conveyor belt placement to three-dimensional workspace manipulation, allowing robots to access items in cluttered mixes from multiple angles and depths. This dimensional expansion enables sophisticated grasping strategies for items that would be inaccessible in traditional planar sorting configurations.
3Extent of automation
If robotic arms navigate cluttered workspaces, then automation is achieved, but collision risks with items and equipment increase
Solution Approach 1:
The robotic system employs dynamic trajectory planning that continuously adapts to the current state of the workspace. As items are moved and workspace conditions change, the system recalculates paths in real-time to maintain safe distances from items and equipment, dynamically adjusting speeds and trajectories to prevent collisions while maintaining automated operation.
Solution Approach 2:
The system uses continuous sensor feedback to monitor the positions of items and robotic components throughout the workspace. This real-time information feeds back to the planning system, which adjusts trajectories and operational parameters to avoid collisions, creating a closed-loop control system that actively prevents harmful interactions.
4Productivity
If multiple robots operate at a workstation, then collective throughput increases, but coordination complexity and collision risks between robots increase
Solution Approach 1:
The workspace is divided into distinct operational zones or regions, with each robot assigned to specific areas or task types. This spatial and functional segmentation reduces the complexity of coordinating multiple robots by limiting their interaction domains, thereby enabling higher collective throughput with manageable coordination overhead.
Data Source
AI summary
A robotic singulation system is disclosed. In various embodiments, sensor data including data associated with an item present in a workspace is received. The sensor data is used to determine and implement a plan to autonomously operate a robotic structure to move and place the item singly in a corresponding location in a singulation conveyance structure. The plan takes into consideration an attribute of the item determined based at least in part on the sensor data.