Resumé

The project is concerned with research in adaptive learning algorithms. The algorithms will enable robots to react to variations in input, perform ongoing corrections during operations and make adjustments to subsequent operations based on evaluation of the output.
In processes such as the slaughtering of animals and processing of meat, the carcasses and cuts vary in size and composition. The traditional control systems for automatic processes in slaughterhouses rely on strict standardization of these products. When this cannot be guaranteed, automation is either abandoned or large margins of error are introduced, resulting in high cost and suboptimal utilization of the resources. Moreover, customers require that the end-product is customized according to their individual preferences, something traditional automated systems have difficulties handling. With large variations in both input and output, an adaptive robot platform is preferable to more dedicated production machinery.
OriginalsprogEngelsk
Titel6th Aalborg U Robotics Workshop
Antal sider1
Publikationsdato27 nov. 2017
Sider16
StatusUdgivet - 27 nov. 2017
Begivenhed6th Aalborg U Robotics Workshop - Aalborg, Danmark
Varighed: 27 nov. 201727 nov. 2017

Konference

Konference6th Aalborg U Robotics Workshop
LandDanmark
ByAalborg
Periode27/11/201727/11/2017

Fingerprint

Robot learning
Intelligent robots
Meats
Adaptive algorithms
Standardization
Learning algorithms
Machinery
Animals
Automation
Robots
Control systems
Processing
Chemical analysis
Costs

Citer dette

@inbook{42e57e678d134a86a8a0a2e0ffa1da06,
title = "Adaptive and Self-learning Slaughter Robots",
abstract = "The project is concerned with research in adaptive learning algorithms. The algorithms will enable robots to react to variations in input, perform ongoing corrections during operations and make adjustments to subsequent operations based on evaluation of the output.In processes such as the slaughtering of animals and processing of meat, the carcasses and cuts vary in size and composition. The traditional control systems for automatic processes in slaughterhouses rely on strict standardization of these products. When this cannot be guaranteed, automation is either abandoned or large margins of error are introduced, resulting in high cost and suboptimal utilization of the resources. Moreover, customers require that the end-product is customized according to their individual preferences, something traditional automated systems have difficulties handling. With large variations in both input and output, an adaptive robot platform is preferable to more dedicated production machinery.",
author = "Philipsen, {Mark Philip} and Andersen, {Rasmus Skovgaard} and Ole Madsen and Moeslund, {Thomas B.}",
year = "2017",
month = "11",
day = "27",
language = "English",
pages = "16",
booktitle = "6th Aalborg U Robotics Workshop",

}

Philipsen, MP, Andersen, RS, Madsen, O & Moeslund, TB 2017, Adaptive and Self-learning Slaughter Robots. i 6th Aalborg U Robotics Workshop. s. 16, 6th Aalborg U Robotics Workshop, Aalborg, Danmark, 27/11/2017.

Adaptive and Self-learning Slaughter Robots. / Philipsen, Mark Philip; Andersen, Rasmus Skovgaard; Madsen, Ole; Moeslund, Thomas B.

6th Aalborg U Robotics Workshop. 2017. s. 16.

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceabstrakt i proceedingForskning

TY - ABST

T1 - Adaptive and Self-learning Slaughter Robots

AU - Philipsen, Mark Philip

AU - Andersen, Rasmus Skovgaard

AU - Madsen, Ole

AU - Moeslund, Thomas B.

PY - 2017/11/27

Y1 - 2017/11/27

N2 - The project is concerned with research in adaptive learning algorithms. The algorithms will enable robots to react to variations in input, perform ongoing corrections during operations and make adjustments to subsequent operations based on evaluation of the output.In processes such as the slaughtering of animals and processing of meat, the carcasses and cuts vary in size and composition. The traditional control systems for automatic processes in slaughterhouses rely on strict standardization of these products. When this cannot be guaranteed, automation is either abandoned or large margins of error are introduced, resulting in high cost and suboptimal utilization of the resources. Moreover, customers require that the end-product is customized according to their individual preferences, something traditional automated systems have difficulties handling. With large variations in both input and output, an adaptive robot platform is preferable to more dedicated production machinery.

AB - The project is concerned with research in adaptive learning algorithms. The algorithms will enable robots to react to variations in input, perform ongoing corrections during operations and make adjustments to subsequent operations based on evaluation of the output.In processes such as the slaughtering of animals and processing of meat, the carcasses and cuts vary in size and composition. The traditional control systems for automatic processes in slaughterhouses rely on strict standardization of these products. When this cannot be guaranteed, automation is either abandoned or large margins of error are introduced, resulting in high cost and suboptimal utilization of the resources. Moreover, customers require that the end-product is customized according to their individual preferences, something traditional automated systems have difficulties handling. With large variations in both input and output, an adaptive robot platform is preferable to more dedicated production machinery.

M3 - Conference abstract in proceeding

SP - 16

BT - 6th Aalborg U Robotics Workshop

ER -