Vision-Guided Parcel Sortation With Dynamic Bin Assignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current parcel sortation systems are inefficient and inflexible, requiring a large number of collection bins and relying heavily on human labor, which limits throughput and increases costs.
Innovation Solution
A processing system that includes a perception system for identifying objects and a primary transport system for conveying objects to designated processing locations, allowing for dynamic assignment of objects to collection bins and efficient sorting without the need for a large number of fixed bins.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a large number of collection bins are used to handle diverse objects, then the system can accommodate more object types, but the physical space and capital costs increase significantly
Solution Approach 1:
The patent implements dynamic bin assignment where collection bins are not permanently dedicated to specific object types but are temporarily assigned based on real-time sortation needs. The system controller dynamically reconfigures which bin receives which object type, allowing the same physical bin to serve multiple object types sequentially. This dynamic approach enables the system to handle diverse object types with fewer physical bins, directly resolving the contradiction between versatility and space requirements
Solution Approach 2:
The system introduces the time dimension to the sortation process by implementing multi-pass sortation. Instead of requiring all object types to be simultaneously accessible (spatial dimension only), objects can be sorted in multiple passes where different object types are handled at different times. This temporal dimension allows the system to accommodate more object types than the number of physical bins, as bins are reused across different time periods for different object categories
2Adaptability or versatility
If human workers manually sort parcels, then flexibility in handling various objects is maintained, but throughput and productivity are limited
Solution Approach 1:
The system implements automated object identification using vision systems and sensors that automatically detect, classify, and track objects as they move through the conveyor. This self-service capability eliminates the need for human workers to manually identify and sort each object, while maintaining flexibility through advanced image recognition algorithms that can handle diverse object types. The automation directly increases throughput while preserving adaptability
Solution Approach 2:
The patent replaces manual human sorting (mechanical/manual system) with an automated control system that uses computer vision, sensors, and programmable logic to identify and direct objects to appropriate bins. This substitution of mechanical/manual operations with automated electronic control systems dramatically increases throughput while maintaining the flexibility to handle various object types through software-based classification rules
3Device complexity
If fixed sequence operations are used in sortation systems, then process control is simplified, but the system becomes inflexible in handling varying object types and sizes
Solution Approach 1:
The system employs dynamic bin assignment where the target bin for each object is determined in real-time based on the object's identified type, size, and current position in the sortation sequence. Rather than following a fixed predetermined sequence, the control system dynamically adjusts which bin receives which object based on real-time conditions, allowing flexible handling of varying object types while maintaining coordinated control through the central controller
4Extent of automation
If recirculating conveyors with tilt trays are used, then automation level increases, but the system requires objects to be singulated and coded, limiting flexibility
Solution Approach 1:
The patent replaces mechanical tilt-tray diversion mechanisms with an automated robotic picking system that uses vision-guided end-effectors to grasp and place objects directly into target bins. This substitution eliminates the requirement for objects to be singulated into single-file streams or to have machine-readable codes, as the vision system can identify objects directly from the conveyor stream. The robotic system maintains high automation while significantly increasing flexibility in handling diverse object types without requiring preprocessing
Data Source
AI summary
A processing system is disclosed for processing objects. The processing system includes a perception system for providing perception data regarding an object, and a primary transport system for providing transport of the object along a primary direction toward a processing location that is identified based on the perception data.