Machine Vision-Assisted Design of End Effector Pose in Robotic Mixed Depalletizing of Heterogeneous Cargo

Automated depalletizing systems aim to offer continuous and efficient operation in warehouse logistics, reducing cycle times and contributing to worker safety. However, most commercially available depalletizing solutions are designed primarily for highly homogeneous cargo arranged in orthogonal conf...

Full description

Saved in:
Bibliographic Details
Main Authors: Sebastián Valero, Juan Camilo Martinez, Ana María Montes, Cesar Marín, Rubén Bolaños, David Álvarez
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/4/1137
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850082317168541696
author Sebastián Valero
Juan Camilo Martinez
Ana María Montes
Cesar Marín
Rubén Bolaños
David Álvarez
author_facet Sebastián Valero
Juan Camilo Martinez
Ana María Montes
Cesar Marín
Rubén Bolaños
David Álvarez
author_sort Sebastián Valero
collection DOAJ
description Automated depalletizing systems aim to offer continuous and efficient operation in warehouse logistics, reducing cycle times and contributing to worker safety. However, most commercially available depalletizing solutions are designed primarily for highly homogeneous cargo arranged in orthogonal configurations. This paper presents a real-time approach for depalletizing heterogeneous pallets with boxes of varying sizes and arbitrary orientations, including configurations where the topmost surfaces of boxes are not necessarily parallel to each other. To accomplish this, we propose an algorithm that leverages deep learning-based machine vision to determine the size, position, and orientation of boxes relative to the horizontal plane of a robot arm from sparse depth data. Using this information, we implement a path planning method that generates collision-free trajectories to enable precise box grasping and placement onto a production line. Validation through both simulated and real-world experiments demonstrates the feasibility and accuracy of this approach in complex industrial settings, highlighting potential improvements in the efficiency and adaptability of automated depalletizing systems.
format Article
id doaj-art-c7ea29a0bca949bbab44e341d8a8e9a6
institution DOAJ
issn 1424-8220
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-c7ea29a0bca949bbab44e341d8a8e9a62025-08-20T02:44:33ZengMDPI AGSensors1424-82202025-02-01254113710.3390/s25041137Machine Vision-Assisted Design of End Effector Pose in Robotic Mixed Depalletizing of Heterogeneous CargoSebastián Valero0Juan Camilo Martinez1Ana María Montes2Cesar Marín3Rubén Bolaños4David Álvarez5Department of Industrial Engineering, Universidad de los Andes, Bogotá 111711, ColombiaDepartment of Industrial Engineering, Universidad de los Andes, Bogotá 111711, ColombiaDepartment of Industrial Engineering, Universidad de los Andes, Bogotá 111711, ColombiaIntegra S.A., Pereira 660003, ColombiaIntegra S.A., Pereira 660003, ColombiaDepartment of Industrial Engineering, Universidad de los Andes, Bogotá 111711, ColombiaAutomated depalletizing systems aim to offer continuous and efficient operation in warehouse logistics, reducing cycle times and contributing to worker safety. However, most commercially available depalletizing solutions are designed primarily for highly homogeneous cargo arranged in orthogonal configurations. This paper presents a real-time approach for depalletizing heterogeneous pallets with boxes of varying sizes and arbitrary orientations, including configurations where the topmost surfaces of boxes are not necessarily parallel to each other. To accomplish this, we propose an algorithm that leverages deep learning-based machine vision to determine the size, position, and orientation of boxes relative to the horizontal plane of a robot arm from sparse depth data. Using this information, we implement a path planning method that generates collision-free trajectories to enable precise box grasping and placement onto a production line. Validation through both simulated and real-world experiments demonstrates the feasibility and accuracy of this approach in complex industrial settings, highlighting potential improvements in the efficiency and adaptability of automated depalletizing systems.https://www.mdpi.com/1424-8220/25/4/1137segmentationhand–eye calibrationrobotic depalletizingheterogeneous cargo handlingdeep learning in roboticssparse stereo vision
spellingShingle Sebastián Valero
Juan Camilo Martinez
Ana María Montes
Cesar Marín
Rubén Bolaños
David Álvarez
Machine Vision-Assisted Design of End Effector Pose in Robotic Mixed Depalletizing of Heterogeneous Cargo
Sensors
segmentation
hand–eye calibration
robotic depalletizing
heterogeneous cargo handling
deep learning in robotics
sparse stereo vision
title Machine Vision-Assisted Design of End Effector Pose in Robotic Mixed Depalletizing of Heterogeneous Cargo
title_full Machine Vision-Assisted Design of End Effector Pose in Robotic Mixed Depalletizing of Heterogeneous Cargo
title_fullStr Machine Vision-Assisted Design of End Effector Pose in Robotic Mixed Depalletizing of Heterogeneous Cargo
title_full_unstemmed Machine Vision-Assisted Design of End Effector Pose in Robotic Mixed Depalletizing of Heterogeneous Cargo
title_short Machine Vision-Assisted Design of End Effector Pose in Robotic Mixed Depalletizing of Heterogeneous Cargo
title_sort machine vision assisted design of end effector pose in robotic mixed depalletizing of heterogeneous cargo
topic segmentation
hand–eye calibration
robotic depalletizing
heterogeneous cargo handling
deep learning in robotics
sparse stereo vision
url https://www.mdpi.com/1424-8220/25/4/1137
work_keys_str_mv AT sebastianvalero machinevisionassisteddesignofendeffectorposeinroboticmixeddepalletizingofheterogeneouscargo
AT juancamilomartinez machinevisionassisteddesignofendeffectorposeinroboticmixeddepalletizingofheterogeneouscargo
AT anamariamontes machinevisionassisteddesignofendeffectorposeinroboticmixeddepalletizingofheterogeneouscargo
AT cesarmarin machinevisionassisteddesignofendeffectorposeinroboticmixeddepalletizingofheterogeneouscargo
AT rubenbolanos machinevisionassisteddesignofendeffectorposeinroboticmixeddepalletizingofheterogeneouscargo
AT davidalvarez machinevisionassisteddesignofendeffectorposeinroboticmixeddepalletizingofheterogeneouscargo