System for conveyor belt part picking using structured light and 3D pose estimation

Thielemann, Jens T.; Skotheim, Øystein; Nygaard, Jens Olav; Vollset, Thor

doi:10.1117/12.805825

Cited by 4 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another example is an ICP-inspired algorithm for retinal image registration [ 21 ]. Robotics has also observed an increasing application of registration problems prominent in pick and place robots such as in [ 22 ], demonstrating the ability to sort products with a random pose on a conveyor belt. The mining industry uses registration in an attempt to automate the stages of the excavator loading cycle.…”

Section: Related Workmentioning

confidence: 99%

Real-Time 6-DOF Pose Estimation of Known Geometries in Point Cloud Data

Bhandari

Phillips

McĂree

2023

Sensors

View full text Add to dashboard Cite

The task of tracking the pose of an object with a known geometry from point cloud measurements arises in robot perception. It calls for a solution that is both accurate and robust, and can be computed at a rate that aligns with the needs of a control system that might make decisions based on it. The Iterative Closest Point (ICP) algorithm is widely used for this purpose, but it is susceptible to failure in practical scenarios. We present a robust and efficient solution for pose-from-point cloud estimation called the Pose Lookup Method (PLuM). PLuM is a probabilistic reward-based objective function that is resilient to measurement uncertainty and clutter. Efficiency is achieved through the use of lookup tables, which substitute complex geometric operations such as raycasting used in earlier solutions. Our results show millimetre accuracy and fast pose estimation in benchmark tests using triangulated geometry models, outperforming state-of-the-art ICP-based methods. These results are extended to field robotics applications, resulting in real-time haul truck pose estimation. By utilising point clouds from a LiDAR fixed to a rope shovel, the PLuM algorithm tracks a haul truck effectively throughout the excavation load cycle at a rate of 20 Hz, matching the sensor frame rate. PLuM is straightforward to implement and provides dependable and timely solutions in demanding environments.

show abstract

Section: Related Workmentioning

confidence: 99%

Real-Time 6-DOF Pose Estimation of Known Geometries in Point Cloud Data

Bhandari

Phillips

McĂree

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The Kalman estimator determines the pose of the object at the moment of pick up considering the noise that is caused by the motion of the conveyor belt since the parts are located there. Thielemann et al (2009) also remove industrial components from a conveyor belt using structured light and 3D pose estimation via CAD modelling. This literature review shows the importance of vision algorithms as part of the bin‐picking task.…”

Section: Introductionmentioning

confidence: 99%

Introducing a new 3D ordering process for discrete food products using food categorisation

Würdemann

Aminzadeh

Dai³

et al. 2010

Industrial Robot: An International Journal

View full text Add to dashboard Cite

PurposeThis paper aims to introduce and identify a new 3D handling operation (bin picking) for natural discrete food products using food categorisation.Design/methodology/approachThe research shows a new food categorisation and the relation between food ordering processes and food categories. Bin picking in the food industry needs more flexible vision software compared to the manufacturing industry in order to decrease the degree of disarray of food products and transfer them into structure.FindingsIt has been shown that there are still manual operated ordering processes in food industry such as bin picking; it just needs new ideas of image processing algorithms such as active shape models (ASMs) on its development in order to recognise the highly varying shapes of food products.Research limitations/implicationsThis research was aimed at locating a new ordering process and proving a new principle, but for practical implementation this bin picking solution needs to be developed and tested further.Originality/valueIdentifying new ordering processes via food categorisation is unique and applying ASMs to bin picking opens a new industrial sector (food industry) for 3D handling.

show abstract

“…The Kalman estimator determines the pose of the object at the moment of pick up considering the noise that is caused by the motion of the conveyor belt since the parts are located there. Thielemann et al [24] also remove industrial components from a conveyor belt using structured light and 3D pose estimation via CAD modelling. This literature review shows the importance of vision algorithms as part of the bin picking task.…”

Section: Introductionmentioning

confidence: 99%

Feature extraction of non-uniform food products using RGB and RGB-D data combined with shape models

Würdemann

Aminzadeh

Cui

et al. 2011

2011 IEEE International Conference on Robotics and Biomimetics

View full text Add to dashboard Cite

Abstract-This research paper investigates a new 3D handling process in food industry: bin picking. Machines only function effectively when the input of product is physically well organised, well structured, and consistent. At many stages in a typical production line, foodstuffs are physically arranged as they move through a machine or equipment, however, this order is then lost again as products are ejected onto conveyors, bulked together into bins for transport, taken off-line for chilled storage. Bin picking is generally not solved for manufacturing parts. Unlike food ordering processes such as pick and place operations, vibratory feeders etc., this food handling operation has not been applied to food industry neither. A new approach is presented using the Microsoft Kinect TM sensor and Active Shape Models. By combining the new device that obtains an RGB and RGB-D image and the flexible shape model, it is possible to identify non-uniform food products that have a high variation in shape. The methodology of this system is presented. The experiments show the achievability of this new system.

show abstract

System for conveyor belt part picking using structured light and 3D pose estimation

Cited by 4 publications

References 8 publications

Real-Time 6-DOF Pose Estimation of Known Geometries in Point Cloud Data

Real-Time 6-DOF Pose Estimation of Known Geometries in Point Cloud Data

Introducing a new 3D ordering process for discrete food products using food categorisation

Feature extraction of non-uniform food products using RGB and RGB-D data combined with shape models

Contact Info

Product

Resources

About