際際滷

際際滷Share a Scribd company logo
CARO Cognitive and Applied Robotics
Grundfos Prize油2015
Presentation油of油our油robotics油research
Professor油Henrik油Gordon油Petersen
Maersk油McKinney油Moller油Institute,油University油of油Southern油Denmark
CARO Cognitive and Applied Robotics
Robots油 some examples
CARO Cognitive and Applied Robotics
Industrial油robots油 some examples
CARO Cognitive and Applied Robotics
Thank you !!
 Grundfos油and油The油Poul油Due油Jensen油Foundation
 The油Assessment油Committee油for油selecting油me油
 The油people that recommended me油to油the油Foundation
CARO Cognitive and Applied Robotics
Thank you !!
 Grundfos油and油The油Poul油Due油Jensen油Foundation
 The油Assessment油Committee油for油selecting油me油
 The油people that recommended me油to油the油Foundation
 My油workplace,油University油of油Southern油Denmark
 My油family,油in油particular油my油wife油Inge,油and油my油children油Mikael油and油Marianne
CARO Cognitive and Applied Robotics
A油bit油about油my油history油in油academia
 MSc油degree油in油Mathematics油and油Physics,油1987
 PhD油degree油in油Applied油Mathematics,油1990油(Topic:油Algorithms油for油
Molecular油Dynamics油Simulations)
 Research油in油Industrial油Robotics油from油around油1991油until油now
 Bilateral油project油with油Odense油Steelshipyard 199196
 Since油1996:油National油and油European油Research&Development projects油with油
Industrial油and油other油academic油partners
 Mission:油Help油as油much油as油I油can油with油developing油robot油technologies油
as油one油of油the油means油to油keep油industrial油production油in油Denmark
CARO Cognitive and Applied Robotics
Two油examples油from油previous油activities
CARO Cognitive and Applied Robotics
Robot油technologies油(not油even油complete)
 Mechanical油Engineering
 Electronics
 Battery油Technology
 Mathematical油Modeling
 Physics
 Sensor油Technology
 Computer油Science
 Artificial油Intelligence
 HumanMachine油Interfaces
 Industry油4.0
CARO Cognitive and Applied Robotics
Luckily,油I油am油not油alone
CARO Cognitive and Applied Robotics
Cognitive油and油Applied油Robotics油Group
CARO Cognitive and Applied Robotics
The油students油on油the油Robot油Technology油
education油(now油at油90油per油year)油
CARO Cognitive and Applied Robotics
Manufacturing油Academy油of油Denmark油(MADE)
CARO Cognitive and Applied Robotics
Human油Workers油vs.油Traditional油Automation
 Human油workers
 Movable so油that they can go油to油where the油work in油the油shopfloor is
 Fast油startup油(hours for油new油tasks,油immediately for油shifts between existing tasks)
 Humans quickly learn how to油improve the油performance油based on油experience
 Easy adaptable to油task modifications
 Traditional automated solutions
 Static big facilities with油fences and油a油lot of油integrated machinery
 Slow startup油(typically in油the油range油of油324油months for油new油tasks)
 Improvement based on油experience is油basically nonexisting
 Difficult to油adapt to油task modifications
 (Much)油too expensive,油i.e.油too long油payback油time油except for油long油term油high runners
CARO Cognitive and Applied Robotics
Goal:油Simple油movable,油reconfigurable,油adaptable油platforms
Movable油and油reconfigurable
A
B
C
D
Adaptable油to油randomly油located油parts
CARO Cognitive and Applied Robotics
Professors油negation油field:油
CARO Cognitive and Applied Robotics
Professors油negation油field:油
Lack油of油uncertainty油handling
CARO Cognitive and Applied Robotics
An油example油of油a油simple油task油
 Posed油by油the油company油
KVMConheat
 Task:油Place油the油two油union油
nuts油on油the油pipe油as油shown
 Several油steps油in油the油task,油
but油main油here油is油on油getting油
the油nuts油onto油the油pipe
 Pipe油and油nut油feeders油used
CARO Cognitive and Applied Robotics
Conventional油teachin油programming油of油the油task油
CARO Cognitive and Applied Robotics
Current油research油topic:油Derive油technologies油for油
facilitating油programming油of油robot油systems油capable油
of油handling油uncertainties
 Mathematical油modeling油of油robot油systems油
 Mathematical油modeling油of油robotic油processes油
 Simulation油and油learning油of油robotic油tasks
 Computer油vision油algorithms
 際際滷s油with油details油on油this油to油follow油now
CARO Cognitive and Applied Robotics
Robot油cell configuration
Virtual油model油(RobWork)
Sequencing
(Mapping to油Semantic Event
Chains油油for油monitoring)
Action油Representation
Simulation油for油vast explorative learning
Learning油for油adjusting in油reality
CARO Cognitive and Applied Robotics
Modeling油of油hardware油for油simulation
CARO Cognitive and Applied Robotics
Action油parametrization
CARO Cognitive and Applied Robotics
Simulation油of油trial油actions:
A油chosen油set油of油action油parameters
A油randomly油chosen油pose油perturbation油
CARO Cognitive and Applied Robotics
Learning油promising油action油parameters:
CARO Cognitive and Applied Robotics
Learned油solution
CARO Cognitive and Applied Robotics
Modular油Robot油cell油for油multiple油tasks油at油Danfoss
 Based油on油a油modular油and油reconfigurable油table
 Goal:油Reconfiguration油between油tasks油to油take油at油most油10油
minutes
 Economically油feasible油automation油of油tasks油which油requires油
much油less油than油full油time油for油human油workers
 Reduction油of油payback油time油per油application
 Challenge:油Program油robot油system油solutions油for油the油processes油
CARO Cognitive and Applied Robotics
Excellent油example油of油MADE油collaboration
CARO Cognitive and Applied Robotics
Modular油Robot油cell油for油multiple油tasks油at油Danfoss
AnyFeeder
Dobb.silo
Emne-
bakke
Presse
Press油together油two油parts油for油a油thermostat油
manual油turning油wheel
Place油thermostats油in油plastic油box
CARO Cognitive and Applied Robotics
Modular油Robot油cell油for油multiple油tasks油at油Danfoss
AnyFeeder
Dobb.silo
Emne-
bakke
Presse
Press油together油two油parts油for油a油thermostat油
manual油turning油wheel
Place油thermostats油in油plastic油box
CARO Cognitive and Applied Robotics
Object油Recognition油and油Pose油Estimation
 Variety油of油algorithms
 Variety油of油sensors
 Variety油of油objects油(material,油
size,油shape,油geometric油
invariants,油etc.)
 Bin油(bulk)油picking油
 Table/feeder油picking
 Strong油research油topic油in油our油
CARO油group油(not油my油main油area油
though)
CARO Cognitive and Applied Robotics
Mini油Picker油
Partners: Scape油Technologies,油Universal油Robots,油Blue油
Ocean油Robotics,油AAU,油DTU,油SDU)
Objective: Create油a油cheap油standardized油bin油picking油
solution油for油small油parts.
Challenges:
 Price
 Design油of油less油pricy油grasping油tool油unit
 Cycle油time
 Automatic油motion油planning
 Pose油estimating油object油in油hand油
 Easy油setup油and油training
 Automatic油grasp油planning
 User油interface
CARO Cognitive and Applied Robotics
Optimize油sensor油configuration油by油modelling油and油simulating油
sensors油and油algorithms.油Input:油Desired油uncertainty油bounds
CARO Cognitive and Applied Robotics
Optimize油sensor油configuration油by油modelling油and油simulating油
sensors油and油algorithms.油Input:油Desired油uncertainty油bounds
 	
 
Where油do油we油get油the油desired油uncertainty油bounds油from油?
CARO Cognitive and Applied Robotics
Uncertainty油propagation油through油assembly油sequence
After油detection
After油grasping
After油placement
CARO Cognitive and Applied Robotics
Handling油layup油of油fiber油plies
Detecting油flaws油with油vision
Learning油to油correct油layup
Computer油simulation
Mathematical油modeling
Selecting油hardware油(drape油tool)
CARO Cognitive and Applied Robotics
Other油application油domains油 Robotic油surgery
o Improve油quality油and油yield油of油
medical油robotics油by:
 Transferring油technology油
and油knowhow油from油
industrial油applications油to油
medical油applications
 Application油driven油
development油
 Close油collaboration油with油
hospitals
CARO Cognitive and Applied Robotics
Other油application油domains油 Welfare油robots
o Robot油assistance油for油disabled油
people:
 Part油of油SPIR油project油
patient@home with油
hospitals,油municipalities,油
etc.
 Potential油is油very油big
 Transfer油of油knowledge油
from油the油industrial油
robotics油domain
CARO Cognitive and Applied Robotics
Thank油you油all油!!

More Related Content

Similar to 2015 Grundfos Prize Lecture (20)

Special Purpose IBM Center of excellence lab
Special Purpose IBM Center of excellence lab Special Purpose IBM Center of excellence lab
Special Purpose IBM Center of excellence lab
Ganesan Narayanasamy
bonino
boninobonino
bonino
Dario Bonino
Constrained Optimization with Genetic Algorithms and Project Bonsai
Constrained Optimization with Genetic Algorithms and Project BonsaiConstrained Optimization with Genetic Algorithms and Project Bonsai
Constrained Optimization with Genetic Algorithms and Project Bonsai
Ivo Andreev
OWF14 - Big Data : The State of Machine Learning in 2014
OWF14 - Big Data : The State of Machine  Learning in 2014OWF14 - Big Data : The State of Machine  Learning in 2014
OWF14 - Big Data : The State of Machine Learning in 2014
Paris Open Source Summit
Cyber-physical systems Industrial applications in the CPSwarm Project
Cyber-physical systems Industrial applications in the CPSwarm ProjectCyber-physical systems Industrial applications in the CPSwarm Project
Cyber-physical systems Industrial applications in the CPSwarm Project
Alessandra Bagnato
From R&D to Market: the industrialization challenge
From R&D to Market: the industrialization challengeFrom R&D to Market: the industrialization challenge
From R&D to Market: the industrialization challenge
QCB-Conference
Yomna Hassan CV 2014
Yomna Hassan CV 2014Yomna Hassan CV 2014
Yomna Hassan CV 2014
Yomna Mahmoud Ibrahim Hassan
Using real and practical oriented training aids in radar technology training
Using real and practical oriented training aids in radar technology trainingUsing real and practical oriented training aids in radar technology training
Using real and practical oriented training aids in radar technology training
TBSS Group
Applied Machine Learning Course - Jodie Zhu (WeCloudData)
Applied Machine Learning Course - Jodie Zhu (WeCloudData)Applied Machine Learning Course - Jodie Zhu (WeCloudData)
Applied Machine Learning Course - Jodie Zhu (WeCloudData)
WeCloudData
Optimization_model_of the propsed kiiraEV assembly lineprstn
Optimization_model_of the propsed kiiraEV assembly lineprstnOptimization_model_of the propsed kiiraEV assembly lineprstn
Optimization_model_of the propsed kiiraEV assembly lineprstn
Ronald Kayiwa
Matlock_Resume_Revised
Matlock_Resume_RevisedMatlock_Resume_Revised
Matlock_Resume_Revised
Alexander Matlock
sample-resume
sample-resumesample-resume
sample-resume
Avinash Malik
TAUS Machine Translation Showcase, The Simplified Guide to Getting Started in...
TAUS Machine Translation Showcase, The Simplified Guide to Getting Started in...TAUS Machine Translation Showcase, The Simplified Guide to Getting Started in...
TAUS Machine Translation Showcase, The Simplified Guide to Getting Started in...
TAUS - The Language Data Network
Innovative trends in robotics
Innovative trends in roboticsInnovative trends in robotics
Innovative trends in robotics
Design World
freebeersessions #26 Scaling Up and Out Using Open Source at Netstar
freebeersessions #26 Scaling Up and Out Using Open Source at Netstarfreebeersessions #26 Scaling Up and Out Using Open Source at Netstar
freebeersessions #26 Scaling Up and Out Using Open Source at Netstar
Quintin de Kok
L4MS Webinar - All you need to know (25th Oct)
L4MS Webinar - All you need to know (25th Oct)L4MS Webinar - All you need to know (25th Oct)
L4MS Webinar - All you need to know (25th Oct)
L4MS
Maintaining SLOs of Cloud-native Applications via Self-Adaptive Resource Sharing
Maintaining SLOs of Cloud-native Applications via Self-Adaptive Resource SharingMaintaining SLOs of Cloud-native Applications via Self-Adaptive Resource Sharing
Maintaining SLOs of Cloud-native Applications via Self-Adaptive Resource Sharing
Vladimir Podolskiy
SVTL 2011 - 16 - Goodwin, Darkwah (RPI-KNUST)
SVTL 2011 - 16 - Goodwin, Darkwah (RPI-KNUST)SVTL 2011 - 16 - Goodwin, Darkwah (RPI-KNUST)
SVTL 2011 - 16 - Goodwin, Darkwah (RPI-KNUST)
the nciia
Student Industrial Training Presentation 際際滷
Student Industrial Training Presentation 際際滷Student Industrial Training Presentation 際際滷
Student Industrial Training Presentation 際際滷
Khairul Filhan
BSC presentation for Festibity Sponsors
BSC presentation for Festibity SponsorsBSC presentation for Festibity Sponsors
BSC presentation for Festibity Sponsors
Festibity
Special Purpose IBM Center of excellence lab
Special Purpose IBM Center of excellence lab Special Purpose IBM Center of excellence lab
Special Purpose IBM Center of excellence lab
Ganesan Narayanasamy
Constrained Optimization with Genetic Algorithms and Project Bonsai
Constrained Optimization with Genetic Algorithms and Project BonsaiConstrained Optimization with Genetic Algorithms and Project Bonsai
Constrained Optimization with Genetic Algorithms and Project Bonsai
Ivo Andreev
OWF14 - Big Data : The State of Machine Learning in 2014
OWF14 - Big Data : The State of Machine  Learning in 2014OWF14 - Big Data : The State of Machine  Learning in 2014
OWF14 - Big Data : The State of Machine Learning in 2014
Paris Open Source Summit
Cyber-physical systems Industrial applications in the CPSwarm Project
Cyber-physical systems Industrial applications in the CPSwarm ProjectCyber-physical systems Industrial applications in the CPSwarm Project
Cyber-physical systems Industrial applications in the CPSwarm Project
Alessandra Bagnato
From R&D to Market: the industrialization challenge
From R&D to Market: the industrialization challengeFrom R&D to Market: the industrialization challenge
From R&D to Market: the industrialization challenge
QCB-Conference
Using real and practical oriented training aids in radar technology training
Using real and practical oriented training aids in radar technology trainingUsing real and practical oriented training aids in radar technology training
Using real and practical oriented training aids in radar technology training
TBSS Group
Applied Machine Learning Course - Jodie Zhu (WeCloudData)
Applied Machine Learning Course - Jodie Zhu (WeCloudData)Applied Machine Learning Course - Jodie Zhu (WeCloudData)
Applied Machine Learning Course - Jodie Zhu (WeCloudData)
WeCloudData
Optimization_model_of the propsed kiiraEV assembly lineprstn
Optimization_model_of the propsed kiiraEV assembly lineprstnOptimization_model_of the propsed kiiraEV assembly lineprstn
Optimization_model_of the propsed kiiraEV assembly lineprstn
Ronald Kayiwa
TAUS Machine Translation Showcase, The Simplified Guide to Getting Started in...
TAUS Machine Translation Showcase, The Simplified Guide to Getting Started in...TAUS Machine Translation Showcase, The Simplified Guide to Getting Started in...
TAUS Machine Translation Showcase, The Simplified Guide to Getting Started in...
TAUS - The Language Data Network
Innovative trends in robotics
Innovative trends in roboticsInnovative trends in robotics
Innovative trends in robotics
Design World
freebeersessions #26 Scaling Up and Out Using Open Source at Netstar
freebeersessions #26 Scaling Up and Out Using Open Source at Netstarfreebeersessions #26 Scaling Up and Out Using Open Source at Netstar
freebeersessions #26 Scaling Up and Out Using Open Source at Netstar
Quintin de Kok
L4MS Webinar - All you need to know (25th Oct)
L4MS Webinar - All you need to know (25th Oct)L4MS Webinar - All you need to know (25th Oct)
L4MS Webinar - All you need to know (25th Oct)
L4MS
Maintaining SLOs of Cloud-native Applications via Self-Adaptive Resource Sharing
Maintaining SLOs of Cloud-native Applications via Self-Adaptive Resource SharingMaintaining SLOs of Cloud-native Applications via Self-Adaptive Resource Sharing
Maintaining SLOs of Cloud-native Applications via Self-Adaptive Resource Sharing
Vladimir Podolskiy
SVTL 2011 - 16 - Goodwin, Darkwah (RPI-KNUST)
SVTL 2011 - 16 - Goodwin, Darkwah (RPI-KNUST)SVTL 2011 - 16 - Goodwin, Darkwah (RPI-KNUST)
SVTL 2011 - 16 - Goodwin, Darkwah (RPI-KNUST)
the nciia
Student Industrial Training Presentation 際際滷
Student Industrial Training Presentation 際際滷Student Industrial Training Presentation 際際滷
Student Industrial Training Presentation 際際滷
Khairul Filhan
BSC presentation for Festibity Sponsors
BSC presentation for Festibity SponsorsBSC presentation for Festibity Sponsors
BSC presentation for Festibity Sponsors
Festibity

Recently uploaded (20)

Computational Photography: How Technology is Changing Way We Capture the World
Computational Photography: How Technology is Changing Way We Capture the WorldComputational Photography: How Technology is Changing Way We Capture the World
Computational Photography: How Technology is Changing Way We Capture the World
HusseinMalikMammadli
A Framework for Model-Driven Digital Twin Engineering
A Framework for Model-Driven Digital Twin EngineeringA Framework for Model-Driven Digital Twin Engineering
A Framework for Model-Driven Digital Twin Engineering
Daniel Lehner
DevNexus - Building 10x Development Organizations.pdf
DevNexus - Building 10x Development Organizations.pdfDevNexus - Building 10x Development Organizations.pdf
DevNexus - Building 10x Development Organizations.pdf
Justin Reock
BoxLang JVM Language : The Future is Dynamic
BoxLang JVM Language : The Future is DynamicBoxLang JVM Language : The Future is Dynamic
BoxLang JVM Language : The Future is Dynamic
Ortus Solutions, Corp
UiPath Automation Developer Associate Training Series 2025 - Session 1
UiPath Automation Developer Associate Training Series 2025 - Session 1UiPath Automation Developer Associate Training Series 2025 - Session 1
UiPath Automation Developer Associate Training Series 2025 - Session 1
DianaGray10
30B Images and Counting: Scaling Canva's Content-Understanding Pipelines by K...
30B Images and Counting: Scaling Canva's Content-Understanding Pipelines by K...30B Images and Counting: Scaling Canva's Content-Understanding Pipelines by K...
30B Images and Counting: Scaling Canva's Content-Understanding Pipelines by K...
ScyllaDB
Cloud of everything Tech of the 21 century in Aviation
Cloud of everything Tech of the 21 century in AviationCloud of everything Tech of the 21 century in Aviation
Cloud of everything Tech of the 21 century in Aviation
Assem mousa
Backstage Software Templates for Java Developers
Backstage Software Templates for Java DevelopersBackstage Software Templates for Java Developers
Backstage Software Templates for Java Developers
Markus Eisele
Q4 2024 Earnings and Investor Presentation
Q4 2024 Earnings and Investor PresentationQ4 2024 Earnings and Investor Presentation
Q4 2024 Earnings and Investor Presentation
Dropbox
How Discord Indexes Trillions of Messages: Scaling Search Infrastructure by V...
How Discord Indexes Trillions of Messages: Scaling Search Infrastructure by V...How Discord Indexes Trillions of Messages: Scaling Search Infrastructure by V...
How Discord Indexes Trillions of Messages: Scaling Search Infrastructure by V...
ScyllaDB
UiPath Automation Developer Associate Training Series 2025 - Session 2
UiPath Automation Developer Associate Training Series 2025 - Session 2UiPath Automation Developer Associate Training Series 2025 - Session 2
UiPath Automation Developer Associate Training Series 2025 - Session 2
DianaGray10
Brave Browser Crack 1.45.133 Activated 2025
Brave Browser Crack 1.45.133 Activated 2025Brave Browser Crack 1.45.133 Activated 2025
Brave Browser Crack 1.45.133 Activated 2025
kherorpacca00126
Understanding Traditional AI with Custom Vision & MuleSoft.pptx
Understanding Traditional AI with Custom Vision & MuleSoft.pptxUnderstanding Traditional AI with Custom Vision & MuleSoft.pptx
Understanding Traditional AI with Custom Vision & MuleSoft.pptx
shyamraj55
Stronger Together: Combining Data Quality and Governance for Confident AI & A...
Stronger Together: Combining Data Quality and Governance for Confident AI & A...Stronger Together: Combining Data Quality and Governance for Confident AI & A...
Stronger Together: Combining Data Quality and Governance for Confident AI & A...
Precisely
Fl studio crack version 12.9 Free Download
Fl studio crack version 12.9 Free DownloadFl studio crack version 12.9 Free Download
Fl studio crack version 12.9 Free Download
kherorpacca127
What Makes "Deep Research"? A Dive into AI Agents
What Makes "Deep Research"? A Dive into AI AgentsWhat Makes "Deep Research"? A Dive into AI Agents
What Makes "Deep Research"? A Dive into AI Agents
Zilliz
SMART SENTRY CYBER THREAT INTELLIGENCE IN IIOT
SMART SENTRY CYBER THREAT INTELLIGENCE IN IIOTSMART SENTRY CYBER THREAT INTELLIGENCE IN IIOT
SMART SENTRY CYBER THREAT INTELLIGENCE IN IIOT
TanmaiArni
FinTech - US Annual Funding Report - 2024.pptx
FinTech - US Annual Funding Report - 2024.pptxFinTech - US Annual Funding Report - 2024.pptx
FinTech - US Annual Funding Report - 2024.pptx
Tracxn
Endpoint Backup: 3 Reasons MSPs Ignore It
Endpoint Backup: 3 Reasons MSPs Ignore ItEndpoint Backup: 3 Reasons MSPs Ignore It
Endpoint Backup: 3 Reasons MSPs Ignore It
MSP360
Both Feet on the Ground - Generative Artificial Intelligence
Both Feet on the Ground - Generative Artificial IntelligenceBoth Feet on the Ground - Generative Artificial Intelligence
Both Feet on the Ground - Generative Artificial Intelligence
Pete Nieminen
Computational Photography: How Technology is Changing Way We Capture the World
Computational Photography: How Technology is Changing Way We Capture the WorldComputational Photography: How Technology is Changing Way We Capture the World
Computational Photography: How Technology is Changing Way We Capture the World
HusseinMalikMammadli
A Framework for Model-Driven Digital Twin Engineering
A Framework for Model-Driven Digital Twin EngineeringA Framework for Model-Driven Digital Twin Engineering
A Framework for Model-Driven Digital Twin Engineering
Daniel Lehner
DevNexus - Building 10x Development Organizations.pdf
DevNexus - Building 10x Development Organizations.pdfDevNexus - Building 10x Development Organizations.pdf
DevNexus - Building 10x Development Organizations.pdf
Justin Reock
BoxLang JVM Language : The Future is Dynamic
BoxLang JVM Language : The Future is DynamicBoxLang JVM Language : The Future is Dynamic
BoxLang JVM Language : The Future is Dynamic
Ortus Solutions, Corp
UiPath Automation Developer Associate Training Series 2025 - Session 1
UiPath Automation Developer Associate Training Series 2025 - Session 1UiPath Automation Developer Associate Training Series 2025 - Session 1
UiPath Automation Developer Associate Training Series 2025 - Session 1
DianaGray10
30B Images and Counting: Scaling Canva's Content-Understanding Pipelines by K...
30B Images and Counting: Scaling Canva's Content-Understanding Pipelines by K...30B Images and Counting: Scaling Canva's Content-Understanding Pipelines by K...
30B Images and Counting: Scaling Canva's Content-Understanding Pipelines by K...
ScyllaDB
Cloud of everything Tech of the 21 century in Aviation
Cloud of everything Tech of the 21 century in AviationCloud of everything Tech of the 21 century in Aviation
Cloud of everything Tech of the 21 century in Aviation
Assem mousa
Backstage Software Templates for Java Developers
Backstage Software Templates for Java DevelopersBackstage Software Templates for Java Developers
Backstage Software Templates for Java Developers
Markus Eisele
Q4 2024 Earnings and Investor Presentation
Q4 2024 Earnings and Investor PresentationQ4 2024 Earnings and Investor Presentation
Q4 2024 Earnings and Investor Presentation
Dropbox
How Discord Indexes Trillions of Messages: Scaling Search Infrastructure by V...
How Discord Indexes Trillions of Messages: Scaling Search Infrastructure by V...How Discord Indexes Trillions of Messages: Scaling Search Infrastructure by V...
How Discord Indexes Trillions of Messages: Scaling Search Infrastructure by V...
ScyllaDB
UiPath Automation Developer Associate Training Series 2025 - Session 2
UiPath Automation Developer Associate Training Series 2025 - Session 2UiPath Automation Developer Associate Training Series 2025 - Session 2
UiPath Automation Developer Associate Training Series 2025 - Session 2
DianaGray10
Brave Browser Crack 1.45.133 Activated 2025
Brave Browser Crack 1.45.133 Activated 2025Brave Browser Crack 1.45.133 Activated 2025
Brave Browser Crack 1.45.133 Activated 2025
kherorpacca00126
Understanding Traditional AI with Custom Vision & MuleSoft.pptx
Understanding Traditional AI with Custom Vision & MuleSoft.pptxUnderstanding Traditional AI with Custom Vision & MuleSoft.pptx
Understanding Traditional AI with Custom Vision & MuleSoft.pptx
shyamraj55
Stronger Together: Combining Data Quality and Governance for Confident AI & A...
Stronger Together: Combining Data Quality and Governance for Confident AI & A...Stronger Together: Combining Data Quality and Governance for Confident AI & A...
Stronger Together: Combining Data Quality and Governance for Confident AI & A...
Precisely
Fl studio crack version 12.9 Free Download
Fl studio crack version 12.9 Free DownloadFl studio crack version 12.9 Free Download
Fl studio crack version 12.9 Free Download
kherorpacca127
What Makes "Deep Research"? A Dive into AI Agents
What Makes "Deep Research"? A Dive into AI AgentsWhat Makes "Deep Research"? A Dive into AI Agents
What Makes "Deep Research"? A Dive into AI Agents
Zilliz
SMART SENTRY CYBER THREAT INTELLIGENCE IN IIOT
SMART SENTRY CYBER THREAT INTELLIGENCE IN IIOTSMART SENTRY CYBER THREAT INTELLIGENCE IN IIOT
SMART SENTRY CYBER THREAT INTELLIGENCE IN IIOT
TanmaiArni
FinTech - US Annual Funding Report - 2024.pptx
FinTech - US Annual Funding Report - 2024.pptxFinTech - US Annual Funding Report - 2024.pptx
FinTech - US Annual Funding Report - 2024.pptx
Tracxn
Endpoint Backup: 3 Reasons MSPs Ignore It
Endpoint Backup: 3 Reasons MSPs Ignore ItEndpoint Backup: 3 Reasons MSPs Ignore It
Endpoint Backup: 3 Reasons MSPs Ignore It
MSP360
Both Feet on the Ground - Generative Artificial Intelligence
Both Feet on the Ground - Generative Artificial IntelligenceBoth Feet on the Ground - Generative Artificial Intelligence
Both Feet on the Ground - Generative Artificial Intelligence
Pete Nieminen

2015 Grundfos Prize Lecture

  • 1. CARO Cognitive and Applied Robotics Grundfos Prize油2015 Presentation油of油our油robotics油research Professor油Henrik油Gordon油Petersen Maersk油McKinney油Moller油Institute,油University油of油Southern油Denmark
  • 2. CARO Cognitive and Applied Robotics Robots油 some examples
  • 3. CARO Cognitive and Applied Robotics Industrial油robots油 some examples
  • 4. CARO Cognitive and Applied Robotics Thank you !! Grundfos油and油The油Poul油Due油Jensen油Foundation The油Assessment油Committee油for油selecting油me油 The油people that recommended me油to油the油Foundation
  • 5. CARO Cognitive and Applied Robotics Thank you !! Grundfos油and油The油Poul油Due油Jensen油Foundation The油Assessment油Committee油for油selecting油me油 The油people that recommended me油to油the油Foundation My油workplace,油University油of油Southern油Denmark My油family,油in油particular油my油wife油Inge,油and油my油children油Mikael油and油Marianne
  • 6. CARO Cognitive and Applied Robotics A油bit油about油my油history油in油academia MSc油degree油in油Mathematics油and油Physics,油1987 PhD油degree油in油Applied油Mathematics,油1990油(Topic:油Algorithms油for油 Molecular油Dynamics油Simulations) Research油in油Industrial油Robotics油from油around油1991油until油now Bilateral油project油with油Odense油Steelshipyard 199196 Since油1996:油National油and油European油Research&Development projects油with油 Industrial油and油other油academic油partners Mission:油Help油as油much油as油I油can油with油developing油robot油technologies油 as油one油of油the油means油to油keep油industrial油production油in油Denmark
  • 7. CARO Cognitive and Applied Robotics Two油examples油from油previous油activities
  • 8. CARO Cognitive and Applied Robotics Robot油technologies油(not油even油complete) Mechanical油Engineering Electronics Battery油Technology Mathematical油Modeling Physics Sensor油Technology Computer油Science Artificial油Intelligence HumanMachine油Interfaces Industry油4.0
  • 9. CARO Cognitive and Applied Robotics Luckily,油I油am油not油alone
  • 10. CARO Cognitive and Applied Robotics Cognitive油and油Applied油Robotics油Group
  • 11. CARO Cognitive and Applied Robotics The油students油on油the油Robot油Technology油 education油(now油at油90油per油year)油
  • 12. CARO Cognitive and Applied Robotics Manufacturing油Academy油of油Denmark油(MADE)
  • 13. CARO Cognitive and Applied Robotics Human油Workers油vs.油Traditional油Automation Human油workers Movable so油that they can go油to油where the油work in油the油shopfloor is Fast油startup油(hours for油new油tasks,油immediately for油shifts between existing tasks) Humans quickly learn how to油improve the油performance油based on油experience Easy adaptable to油task modifications Traditional automated solutions Static big facilities with油fences and油a油lot of油integrated machinery Slow startup油(typically in油the油range油of油324油months for油new油tasks) Improvement based on油experience is油basically nonexisting Difficult to油adapt to油task modifications (Much)油too expensive,油i.e.油too long油payback油time油except for油long油term油high runners
  • 14. CARO Cognitive and Applied Robotics Goal:油Simple油movable,油reconfigurable,油adaptable油platforms Movable油and油reconfigurable A B C D Adaptable油to油randomly油located油parts
  • 15. CARO Cognitive and Applied Robotics Professors油negation油field:油
  • 16. CARO Cognitive and Applied Robotics Professors油negation油field:油 Lack油of油uncertainty油handling
  • 17. CARO Cognitive and Applied Robotics An油example油of油a油simple油task油 Posed油by油the油company油 KVMConheat Task:油Place油the油two油union油 nuts油on油the油pipe油as油shown Several油steps油in油the油task,油 but油main油here油is油on油getting油 the油nuts油onto油the油pipe Pipe油and油nut油feeders油used
  • 18. CARO Cognitive and Applied Robotics Conventional油teachin油programming油of油the油task油
  • 19. CARO Cognitive and Applied Robotics Current油research油topic:油Derive油technologies油for油 facilitating油programming油of油robot油systems油capable油 of油handling油uncertainties Mathematical油modeling油of油robot油systems油 Mathematical油modeling油of油robotic油processes油 Simulation油and油learning油of油robotic油tasks Computer油vision油algorithms 際際滷s油with油details油on油this油to油follow油now
  • 20. CARO Cognitive and Applied Robotics Robot油cell configuration Virtual油model油(RobWork) Sequencing (Mapping to油Semantic Event Chains油油for油monitoring) Action油Representation Simulation油for油vast explorative learning Learning油for油adjusting in油reality
  • 21. CARO Cognitive and Applied Robotics Modeling油of油hardware油for油simulation
  • 22. CARO Cognitive and Applied Robotics Action油parametrization
  • 23. CARO Cognitive and Applied Robotics Simulation油of油trial油actions: A油chosen油set油of油action油parameters A油randomly油chosen油pose油perturbation油
  • 24. CARO Cognitive and Applied Robotics Learning油promising油action油parameters:
  • 25. CARO Cognitive and Applied Robotics Learned油solution
  • 26. CARO Cognitive and Applied Robotics Modular油Robot油cell油for油multiple油tasks油at油Danfoss Based油on油a油modular油and油reconfigurable油table Goal:油Reconfiguration油between油tasks油to油take油at油most油10油 minutes Economically油feasible油automation油of油tasks油which油requires油 much油less油than油full油time油for油human油workers Reduction油of油payback油time油per油application Challenge:油Program油robot油system油solutions油for油the油processes油
  • 27. CARO Cognitive and Applied Robotics Excellent油example油of油MADE油collaboration
  • 28. CARO Cognitive and Applied Robotics Modular油Robot油cell油for油multiple油tasks油at油Danfoss AnyFeeder Dobb.silo Emne- bakke Presse Press油together油two油parts油for油a油thermostat油 manual油turning油wheel Place油thermostats油in油plastic油box
  • 29. CARO Cognitive and Applied Robotics Modular油Robot油cell油for油multiple油tasks油at油Danfoss AnyFeeder Dobb.silo Emne- bakke Presse Press油together油two油parts油for油a油thermostat油 manual油turning油wheel Place油thermostats油in油plastic油box
  • 30. CARO Cognitive and Applied Robotics Object油Recognition油and油Pose油Estimation Variety油of油algorithms Variety油of油sensors Variety油of油objects油(material,油 size,油shape,油geometric油 invariants,油etc.) Bin油(bulk)油picking油 Table/feeder油picking Strong油research油topic油in油our油 CARO油group油(not油my油main油area油 though)
  • 31. CARO Cognitive and Applied Robotics Mini油Picker油 Partners: Scape油Technologies,油Universal油Robots,油Blue油 Ocean油Robotics,油AAU,油DTU,油SDU) Objective: Create油a油cheap油standardized油bin油picking油 solution油for油small油parts. Challenges: Price Design油of油less油pricy油grasping油tool油unit Cycle油time Automatic油motion油planning Pose油estimating油object油in油hand油 Easy油setup油and油training Automatic油grasp油planning User油interface
  • 32. CARO Cognitive and Applied Robotics Optimize油sensor油configuration油by油modelling油and油simulating油 sensors油and油algorithms.油Input:油Desired油uncertainty油bounds
  • 33. CARO Cognitive and Applied Robotics Optimize油sensor油configuration油by油modelling油and油simulating油 sensors油and油algorithms.油Input:油Desired油uncertainty油bounds Where油do油we油get油the油desired油uncertainty油bounds油from油?
  • 34. CARO Cognitive and Applied Robotics Uncertainty油propagation油through油assembly油sequence After油detection After油grasping After油placement
  • 35. CARO Cognitive and Applied Robotics Handling油layup油of油fiber油plies Detecting油flaws油with油vision Learning油to油correct油layup Computer油simulation Mathematical油modeling Selecting油hardware油(drape油tool)
  • 36. CARO Cognitive and Applied Robotics Other油application油domains油 Robotic油surgery o Improve油quality油and油yield油of油 medical油robotics油by: Transferring油technology油 and油knowhow油from油 industrial油applications油to油 medical油applications Application油driven油 development油 Close油collaboration油with油 hospitals
  • 37. CARO Cognitive and Applied Robotics Other油application油domains油 Welfare油robots o Robot油assistance油for油disabled油 people: Part油of油SPIR油project油 patient@home with油 hospitals,油municipalities,油 etc. Potential油is油very油big Transfer油of油knowledge油 from油the油industrial油 robotics油domain
  • 38. CARO Cognitive and Applied Robotics Thank油you油all油!!