Robotic Sortation Using Multi-Modal Object Recognition and Grasp Selection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current sorting systems rely heavily on human intervention and are inefficient in automatically identifying and sorting a variety of objects in dynamic, heterogeneous environments, as they struggle to handle objects with obscured or non-visible barcodes and require manual assistance for optimal grasp selection.

Innovation Solution

A robotic sortation system that employs automated scanners and a robotic arm with perception units, including cameras and depth sensors, to identify objects, determine optimal grasp locations, and plan motion for efficient sorting, allowing human assistance for learning and improving grasp strategies, and utilizing a central computing system for determining destination locations based on object identification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated scanning is used to identify objects, then productivity is improved, but measurement precision deteriorates when barcodes are obscured or non-visible

Engineering Contradiction:
Improvesorting speedVSAvoidobject identification accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The system changes the identification parameter from barcode-only recognition to multi-parameter recognition including visual features, depth information, and geometric properties. This allows objects to be identified even when barcodes are obscured, maintaining high productivity while improving measurement precision through alternative identification parameters.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent introduces perception units (cameras, depth sensors) as intermediaries between the scanning system and objects. These intermediaries capture additional information about objects, enabling identification through multiple modalities when barcodes are not visible, thus resolving the contradiction between automated scanning speed and identification accuracy.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If human operators manually sort objects, then measurement precision is maintained through visual inspection, but productivity decreases due to manual processing

Engineering Contradiction:
Improveobject identification accuracyVSAvoidsorting speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces the mechanical human sorting system with an automated robotic system equipped with perception units and depth sensors. This substitution maintains measurement precision through advanced sensing capabilities while dramatically improving productivity by eliminating manual processing bottlenecks.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables objects to be automatically identified and sorted without human intervention by using perception units to capture object characteristics and the robotic arm to execute sorting actions. This self-service capability maintains accuracy while achieving high-speed automated processing.

Inventive Principle:
Principle #25Self-service

3Productivity

If a robotic arm is used to grasp objects, then productivity is improved through automation, but reliability deteriorates due to difficulty in selecting optimal grasp locations

Engineering Contradiction:
Improveautomation levelVSAvoidgrasp success rate
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent performs preliminary analysis of object geometry and surface properties using depth sensors and perception units before the robotic arm attempts grasping. This preliminary action identifies optimal grasp locations and approaches, ensuring high reliability while maintaining automated productivity.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system incorporates feedback mechanisms where perception units continuously monitor object positions and orientations, and the system adjusts grasp planning based on this feedback. This closed-loop control improves grasp success rates while maintaining high-speed automated operation.

Inventive Principle:
Principle #23Feedback

4Measurement precision

If multiple sensors and perception units are added to improve object identification, then measurement precision is improved, but device complexity increases

Engineering Contradiction:
Improveobject recognition accuracyVSAvoidsystem configuration
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent designs perception units that serve multiple functions: cameras capture visual information for identification, depth sensors provide geometric data for grasp planning, and the same system supports both identification and sorting operations. This multi-functionality reduces overall system complexity while maintaining high measurement precision.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP3374138B1Sortation systems for providing sortation of a variety of obejcts
Publication Date: 2022.08.31 BERKSHIRE GREY OPERATING CO INC
  • EP3374138B1 patent drawingFigure 1
  • EP3374138B1 patent drawingFigure 2
  • EP3374138B1 patent drawingFigure 3

AI summary

A sortation system is disclosed for providing processing of homogenous and non-homogenous objects in both structured and cluttered environments. The sortation system includes a programmable motion device including an end effector, a perception system for recognizing any of the identity, location, and orientation of an object presented in a plurality of objects, a grasp selection system for selecting a grasp location on the object, the grasp location being chosen to provide a secure grasp of the object by the end effector to permit the object to be moved from the plurality of objects to one of a plurality of destination locations, and a motion planning system for providing a motion path for the transport of the object when grasped by the end effector from the plurality of objects to the one of the plurality of destination locations, wherein the motion path is chosen to provide a path from the plurality of objects to the one of the plurality of destination locations.