SlideShare a Scribd company logo
1 of 28
17 July 2015
Industrial Automation
9th June
Chris Roberts
17 July 2015 2
Background
17 July 2015 3
Overview of Cambridge Consultants
We are a world leader in technology and product innovation
 400 engineers, scientists, designers and consultants working from our offices in UK and US
 For clients world wide, we
– develop breakthrough products & systems
– create and license intellectual property
– provide business consulting in technology critical issues
 70% of our work is repeat business – we become trusted partners for our clients
Cambridge MA
Cambridge UK
Singapore
17 July 2015 4
Agenda
What’s the problem we’re trying to solve here?
 Robots are excellent at
– Repetitive tasks
– Hard objects
– Exact dimensions
– Controlled environments
17 July 2015 5
Agenda
What’s the problem we’re trying to solve here?
 Robots are NOT excellent at
– Tasks that change
– Objects that can’t be gripped firmly
– Objects with varying sizes and shapes
– Environments that change
17 July 2015 6
Future world of work research– 2020 to 2030
Will robots steal jobs?
Mature territories
Aging workforce, receding retirement age, expecting better jobs
Networked, integrated warehouse systems
Growing Territories
Highly-mobile workforce with high expectations of a good work-life
balance
Increased uptake of control and automation
Emerging Territories
High turnover of young staff with low technical skills
Remote monitoring of warehouses
17 July 2015 7
Robotics and machine vision
Science vs Engineering
17 July 2015 8
Robotics case study – Amazon picking challenge
“ The winning design was capable of picking up 12 objects in 20 minutes ”
17 July 2015 9
Machine vision case study – ArcAid
 Measures the arc of the throw in real time
 Offers rating, advice
17 July 2015 10
Machine vision case study – ArcAid
17 July 2015 11
Cambridge Consultants
Robotics Project
17 July 2015 12
Agenda
Why are we doing this now?
 Robotics experience
 Low cost sensors and powerful image processing algorithms are available
 Embedded processing power
17 July 2015 13
So, what’s the challenge?
17 July 2015 14
There are three main technical challenges to picking fruit or vegetables in a
warehouse or field:
 Grippers / actuators need to cope with softer objects
 Algorithms and control systems that can cope without
exact models of the environment and objects
 Robots that can interact safely with humans
This project focusses on the first two challenges
17 July 2015 15
Gripper
17 July 2015 16
Custom gripper design
17 July 2015 17
Custom gripper design
17 July 2015 18
Custom gripper design
17 July 2015 19
Vision Processing
17 July 2015 20
Vision system
 Determine which object is on top of a pile of similar objects
 Real time processing of the images and depth maps
 No precise description of the object exists
 The objects are similar but not identical
 Low cost, commodity hardware
 Determine where to place gripper
17 July 2015 21
Vision system
 Load Objects Step
 Process Images Step
17 July 2015 22
Vision system
20 40 60 80 100 120 140 160 180 200
20
40
60
80
100
120
140
160
180
20 40 60 80 100 120 140 160 180 200
20
40
60
80
100
120
140
160
180
 Process Objects Step
17 July 2015 23
Vision system
 Select Objects Step
17 July 2015 24
Conclusions
17 July 2015 25
Getting robots into the field?
 Not quite yet – intermediate step
 The proof of concept stage is not the hard one
 Engineering is as important as the science
17 July 2015 26
Getting robots into the field?
Embedded processor
RTOS
Vision
Driver
Image
Processing
Object
Detection
Robot Movement
Gripper
Vision
Sensor
Object
Sensor
Driver
Low -level
Robot control
Vacuum
Control
Gripper
Control
Robot Arm
Vacuum Pump
and Valves Depth
Sensor
17 July 2015 27
Getting robots into the field?
 Is it worth it?
 For some applications it will be – but there needs to be a
business case
 Development will be expensive
17 July 2015
Cambridge Consultants Ltd
Science Park, Milton Road
Cambridge CB4 0DW
England
Cambridge Consultants Inc
101 Main Street
Cambridge MA 02142
USA
Tel: +44 (0)1223 420024
Fax: +44 (0)1223 423373
Tel: +1 617 532 4700
Fax: +1 617 532 4747 Registered No. 1036296 England
Cambridge Consultants is part of the Altran group,
a global leader in Innovation. www.Altran.com
info@CambridgeConsultants.com
www.CambridgeConsultants.com

More Related Content

Viewers also liked

XAP processor cores
XAP processor coresXAP processor cores
XAP processor corescbturner
 
Supporting innovation & guiding early commercialization
Supporting innovation & guiding early commercializationSupporting innovation & guiding early commercialization
Supporting innovation & guiding early commercializationCambridge Consultants
 
Automated harvesting - is the juice worth the squeeze?
Automated harvesting - is the juice worth the squeeze?Automated harvesting - is the juice worth the squeeze?
Automated harvesting - is the juice worth the squeeze?Cambridge Consultants
 
Does one size fit all...How to develop a wearable
Does one size fit all...How to develop a wearableDoes one size fit all...How to develop a wearable
Does one size fit all...How to develop a wearableCambridge Consultants
 
Synbio start-ups in the uk and worldwide
Synbio start-ups in the uk and worldwideSynbio start-ups in the uk and worldwide
Synbio start-ups in the uk and worldwideCambridge Consultants
 
Satisfying us and eu human factors requirements for inhaler devices
Satisfying us and eu human factors requirements for inhaler devicesSatisfying us and eu human factors requirements for inhaler devices
Satisfying us and eu human factors requirements for inhaler devicesCambridge Consultants
 
The Circular Economy – how can innovation help?
The Circular Economy – how can innovation help?The Circular Economy – how can innovation help?
The Circular Economy – how can innovation help?Cambridge Consultants
 

Viewers also liked (12)

XAP processor cores
XAP processor coresXAP processor cores
XAP processor cores
 
Supporting innovation & guiding early commercialization
Supporting innovation & guiding early commercializationSupporting innovation & guiding early commercialization
Supporting innovation & guiding early commercialization
 
Automated harvesting - is the juice worth the squeeze?
Automated harvesting - is the juice worth the squeeze?Automated harvesting - is the juice worth the squeeze?
Automated harvesting - is the juice worth the squeeze?
 
Does one size fit all...How to develop a wearable
Does one size fit all...How to develop a wearableDoes one size fit all...How to develop a wearable
Does one size fit all...How to develop a wearable
 
Generating insight from data
Generating insight from dataGenerating insight from data
Generating insight from data
 
Skincare Packaging Innovation
Skincare Packaging InnovationSkincare Packaging Innovation
Skincare Packaging Innovation
 
Synbio start-ups in the uk and worldwide
Synbio start-ups in the uk and worldwideSynbio start-ups in the uk and worldwide
Synbio start-ups in the uk and worldwide
 
Developing Sports Technology FAST
  Developing Sports Technology FAST  Developing Sports Technology FAST
Developing Sports Technology FAST
 
Satisfying us and eu human factors requirements for inhaler devices
Satisfying us and eu human factors requirements for inhaler devicesSatisfying us and eu human factors requirements for inhaler devices
Satisfying us and eu human factors requirements for inhaler devices
 
Evolutions to Smart Buildings
Evolutions to Smart BuildingsEvolutions to Smart Buildings
Evolutions to Smart Buildings
 
Does one size fit all
Does one size fit allDoes one size fit all
Does one size fit all
 
The Circular Economy – how can innovation help?
The Circular Economy – how can innovation help?The Circular Economy – how can innovation help?
The Circular Economy – how can innovation help?
 

Similar to Robots - Getting out of factories and into fields

Movebot ENGR245 Lean LaunchPad Stanford 2018
Movebot ENGR245 Lean LaunchPad Stanford 2018Movebot ENGR245 Lean LaunchPad Stanford 2018
Movebot ENGR245 Lean LaunchPad Stanford 2018Stanford University
 
[한국포스트휴먼학회 창립기념 공개강연회 l KAIST 휴머노이드로봇센터 오준호 교수] Robot Technology and the future
[한국포스트휴먼학회 창립기념 공개강연회 l KAIST 휴머노이드로봇센터 오준호 교수] Robot Technology and the future[한국포스트휴먼학회 창립기념 공개강연회 l KAIST 휴머노이드로봇센터 오준호 교수] Robot Technology and the future
[한국포스트휴먼학회 창립기념 공개강연회 l KAIST 휴머노이드로봇센터 오준호 교수] Robot Technology and the futureMINWHO Law Group
 
Throwing IoT in the Trash (literally) - How sensor data, analytics, and AWS c...
Throwing IoT in the Trash (literally) - How sensor data, analytics, and AWS c...Throwing IoT in the Trash (literally) - How sensor data, analytics, and AWS c...
Throwing IoT in the Trash (literally) - How sensor data, analytics, and AWS c...TIBCO Jaspersoft
 
SEKISUI - RFID Journal Live - May 2023.pdf
SEKISUI - RFID Journal Live - May 2023.pdfSEKISUI - RFID Journal Live - May 2023.pdf
SEKISUI - RFID Journal Live - May 2023.pdfRich Rogers
 
A Bigger Magnifying Glass: Analyzing the Internet of Things
A Bigger Magnifying Glass: Analyzing the Internet of Things	A Bigger Magnifying Glass: Analyzing the Internet of Things
A Bigger Magnifying Glass: Analyzing the Internet of Things Eric Kavanagh
 
How we integrate Machine Learning Algorithms into our IT Platform at Outfitte...
How we integrate Machine Learning Algorithms into our IT Platform at Outfitte...How we integrate Machine Learning Algorithms into our IT Platform at Outfitte...
How we integrate Machine Learning Algorithms into our IT Platform at Outfitte...OUTFITTERY
 
GOTO Night: Decision Making Based on Machine Learning
GOTO Night: Decision Making Based on Machine LearningGOTO Night: Decision Making Based on Machine Learning
GOTO Night: Decision Making Based on Machine LearningOUTFITTERY
 
Big data debunking some of the myths
Big data debunking some of the mythsBig data debunking some of the myths
Big data debunking some of the mythsChris Swan
 
IoT Meets Big Data: The Opportunities and Challenges by Syed Hoda of ParStream
IoT Meets Big Data: The Opportunities and Challenges by Syed Hoda of ParStreamIoT Meets Big Data: The Opportunities and Challenges by Syed Hoda of ParStream
IoT Meets Big Data: The Opportunities and Challenges by Syed Hoda of ParStreamgogo6
 
Session T6 - Artificial Intelligence Meets Project Controls
Session T6 - Artificial Intelligence Meets Project ControlsSession T6 - Artificial Intelligence Meets Project Controls
Session T6 - Artificial Intelligence Meets Project ControlsProject Controls Expo
 
Automating Humans back into Aviation
Automating Humans back into AviationAutomating Humans back into Aviation
Automating Humans back into AviationSander De Bree
 
How to Better Manage Technical Debt While Innovating on DevOps
How to Better Manage Technical Debt While Innovating on DevOpsHow to Better Manage Technical Debt While Innovating on DevOps
How to Better Manage Technical Debt While Innovating on DevOpsDynatrace
 
SSFUK Leaders Event 19th April 2018: Artificial Intelligence and the Cognitiv...
SSFUK Leaders Event 19th April 2018: Artificial Intelligence and the Cognitiv...SSFUK Leaders Event 19th April 2018: Artificial Intelligence and the Cognitiv...
SSFUK Leaders Event 19th April 2018: Artificial Intelligence and the Cognitiv...Level
 
Automatski - Industrial Process Monitoring Solution
Automatski - Industrial Process Monitoring SolutionAutomatski - Industrial Process Monitoring Solution
Automatski - Industrial Process Monitoring Solutionautomatskicorporation
 
Predictive Analytics: Why (I)IoT Is Different
Predictive Analytics: Why (I)IoT Is DifferentPredictive Analytics: Why (I)IoT Is Different
Predictive Analytics: Why (I)IoT Is DifferentAltoros
 
Open IoT Made Easy - Introduction to OGC SensorThings API
Open IoT Made Easy - Introduction to OGC SensorThings APIOpen IoT Made Easy - Introduction to OGC SensorThings API
Open IoT Made Easy - Introduction to OGC SensorThings APISensorUp
 
Decision Making based on Machine Learning at Outfittery (W-JAX 2017)
Decision Making based on Machine Learning at Outfittery (W-JAX 2017)Decision Making based on Machine Learning at Outfittery (W-JAX 2017)
Decision Making based on Machine Learning at Outfittery (W-JAX 2017)OUTFITTERY
 
Digital technology as driving force for industry 4.0 and digital economy
Digital technology as driving force for industry 4.0 and digital economyDigital technology as driving force for industry 4.0 and digital economy
Digital technology as driving force for industry 4.0 and digital economySuta Wijaya
 
Innovative trends in robotics
Innovative trends in roboticsInnovative trends in robotics
Innovative trends in roboticsDesign World
 

Similar to Robots - Getting out of factories and into fields (20)

Movebot ENGR245 Lean LaunchPad Stanford 2018
Movebot ENGR245 Lean LaunchPad Stanford 2018Movebot ENGR245 Lean LaunchPad Stanford 2018
Movebot ENGR245 Lean LaunchPad Stanford 2018
 
[한국포스트휴먼학회 창립기념 공개강연회 l KAIST 휴머노이드로봇센터 오준호 교수] Robot Technology and the future
[한국포스트휴먼학회 창립기념 공개강연회 l KAIST 휴머노이드로봇센터 오준호 교수] Robot Technology and the future[한국포스트휴먼학회 창립기념 공개강연회 l KAIST 휴머노이드로봇센터 오준호 교수] Robot Technology and the future
[한국포스트휴먼학회 창립기념 공개강연회 l KAIST 휴머노이드로봇센터 오준호 교수] Robot Technology and the future
 
Throwing IoT in the Trash (literally) - How sensor data, analytics, and AWS c...
Throwing IoT in the Trash (literally) - How sensor data, analytics, and AWS c...Throwing IoT in the Trash (literally) - How sensor data, analytics, and AWS c...
Throwing IoT in the Trash (literally) - How sensor data, analytics, and AWS c...
 
SEKISUI - RFID Journal Live - May 2023.pdf
SEKISUI - RFID Journal Live - May 2023.pdfSEKISUI - RFID Journal Live - May 2023.pdf
SEKISUI - RFID Journal Live - May 2023.pdf
 
A Bigger Magnifying Glass: Analyzing the Internet of Things
A Bigger Magnifying Glass: Analyzing the Internet of Things	A Bigger Magnifying Glass: Analyzing the Internet of Things
A Bigger Magnifying Glass: Analyzing the Internet of Things
 
How we integrate Machine Learning Algorithms into our IT Platform at Outfitte...
How we integrate Machine Learning Algorithms into our IT Platform at Outfitte...How we integrate Machine Learning Algorithms into our IT Platform at Outfitte...
How we integrate Machine Learning Algorithms into our IT Platform at Outfitte...
 
GOTO Night: Decision Making Based on Machine Learning
GOTO Night: Decision Making Based on Machine LearningGOTO Night: Decision Making Based on Machine Learning
GOTO Night: Decision Making Based on Machine Learning
 
Big data debunking some of the myths
Big data debunking some of the mythsBig data debunking some of the myths
Big data debunking some of the myths
 
IoT Meets Big Data: The Opportunities and Challenges by Syed Hoda of ParStream
IoT Meets Big Data: The Opportunities and Challenges by Syed Hoda of ParStreamIoT Meets Big Data: The Opportunities and Challenges by Syed Hoda of ParStream
IoT Meets Big Data: The Opportunities and Challenges by Syed Hoda of ParStream
 
ABB Journey to Digital
ABB Journey to DigitalABB Journey to Digital
ABB Journey to Digital
 
Session T6 - Artificial Intelligence Meets Project Controls
Session T6 - Artificial Intelligence Meets Project ControlsSession T6 - Artificial Intelligence Meets Project Controls
Session T6 - Artificial Intelligence Meets Project Controls
 
Automating Humans back into Aviation
Automating Humans back into AviationAutomating Humans back into Aviation
Automating Humans back into Aviation
 
How to Better Manage Technical Debt While Innovating on DevOps
How to Better Manage Technical Debt While Innovating on DevOpsHow to Better Manage Technical Debt While Innovating on DevOps
How to Better Manage Technical Debt While Innovating on DevOps
 
SSFUK Leaders Event 19th April 2018: Artificial Intelligence and the Cognitiv...
SSFUK Leaders Event 19th April 2018: Artificial Intelligence and the Cognitiv...SSFUK Leaders Event 19th April 2018: Artificial Intelligence and the Cognitiv...
SSFUK Leaders Event 19th April 2018: Artificial Intelligence and the Cognitiv...
 
Automatski - Industrial Process Monitoring Solution
Automatski - Industrial Process Monitoring SolutionAutomatski - Industrial Process Monitoring Solution
Automatski - Industrial Process Monitoring Solution
 
Predictive Analytics: Why (I)IoT Is Different
Predictive Analytics: Why (I)IoT Is DifferentPredictive Analytics: Why (I)IoT Is Different
Predictive Analytics: Why (I)IoT Is Different
 
Open IoT Made Easy - Introduction to OGC SensorThings API
Open IoT Made Easy - Introduction to OGC SensorThings APIOpen IoT Made Easy - Introduction to OGC SensorThings API
Open IoT Made Easy - Introduction to OGC SensorThings API
 
Decision Making based on Machine Learning at Outfittery (W-JAX 2017)
Decision Making based on Machine Learning at Outfittery (W-JAX 2017)Decision Making based on Machine Learning at Outfittery (W-JAX 2017)
Decision Making based on Machine Learning at Outfittery (W-JAX 2017)
 
Digital technology as driving force for industry 4.0 and digital economy
Digital technology as driving force for industry 4.0 and digital economyDigital technology as driving force for industry 4.0 and digital economy
Digital technology as driving force for industry 4.0 and digital economy
 
Innovative trends in robotics
Innovative trends in roboticsInnovative trends in robotics
Innovative trends in robotics
 

More from Cambridge Consultants

The COVID questions – shaping our response for an innovative post-pandemic world
The COVID questions – shaping our response for an innovative post-pandemic worldThe COVID questions – shaping our response for an innovative post-pandemic world
The COVID questions – shaping our response for an innovative post-pandemic worldCambridge Consultants
 
Personalization - is it right for your brand?
Personalization - is it right for your brand?Personalization - is it right for your brand?
Personalization - is it right for your brand?Cambridge Consultants
 
Make or buy? Commercial and technical drivers for vertical farming
Make or buy? Commercial and technical drivers for vertical farmingMake or buy? Commercial and technical drivers for vertical farming
Make or buy? Commercial and technical drivers for vertical farmingCambridge Consultants
 
Forecasting the emerging trends and technologies shaping the industry
Forecasting the emerging trends and technologies shaping the industryForecasting the emerging trends and technologies shaping the industry
Forecasting the emerging trends and technologies shaping the industryCambridge Consultants
 
Encapsulation for industrial applications
Encapsulation for industrial applicationsEncapsulation for industrial applications
Encapsulation for industrial applicationsCambridge Consultants
 
Last mile aerial delivery - will the dream become a reality?
Last mile aerial delivery - will the dream become a reality?Last mile aerial delivery - will the dream become a reality?
Last mile aerial delivery - will the dream become a reality?Cambridge Consultants
 
Beyond the visible - real time crop monitoring at real world speeds
Beyond the visible - real time crop monitoring at real world speedsBeyond the visible - real time crop monitoring at real world speeds
Beyond the visible - real time crop monitoring at real world speedsCambridge Consultants
 
Bluetooth Smart: Connecting Medical Devices to Smart Phones
Bluetooth Smart: Connecting Medical Devices to Smart PhonesBluetooth Smart: Connecting Medical Devices to Smart Phones
Bluetooth Smart: Connecting Medical Devices to Smart PhonesCambridge Consultants
 
Cambridge Consultants Innovation Day 2012: Consumer healthcare and healthy co...
Cambridge Consultants Innovation Day 2012: Consumer healthcare and healthy co...Cambridge Consultants Innovation Day 2012: Consumer healthcare and healthy co...
Cambridge Consultants Innovation Day 2012: Consumer healthcare and healthy co...Cambridge Consultants
 
Cambridge Consultants Innovation Day 2012: Mapping a bright future
Cambridge Consultants Innovation Day 2012: Mapping a bright futureCambridge Consultants Innovation Day 2012: Mapping a bright future
Cambridge Consultants Innovation Day 2012: Mapping a bright futureCambridge Consultants
 
Cambridge Consultants Innovation Day 2012: Innovating for consumers in emergi...
Cambridge Consultants Innovation Day 2012: Innovating for consumers in emergi...Cambridge Consultants Innovation Day 2012: Innovating for consumers in emergi...
Cambridge Consultants Innovation Day 2012: Innovating for consumers in emergi...Cambridge Consultants
 
Cambridge Consultants Innovation Day 2012: Connected machines in a digital ec...
Cambridge Consultants Innovation Day 2012: Connected machines in a digital ec...Cambridge Consultants Innovation Day 2012: Connected machines in a digital ec...
Cambridge Consultants Innovation Day 2012: Connected machines in a digital ec...Cambridge Consultants
 

More from Cambridge Consultants (14)

The COVID questions – shaping our response for an innovative post-pandemic world
The COVID questions – shaping our response for an innovative post-pandemic worldThe COVID questions – shaping our response for an innovative post-pandemic world
The COVID questions – shaping our response for an innovative post-pandemic world
 
Personalization - is it right for your brand?
Personalization - is it right for your brand?Personalization - is it right for your brand?
Personalization - is it right for your brand?
 
Make or buy? Commercial and technical drivers for vertical farming
Make or buy? Commercial and technical drivers for vertical farmingMake or buy? Commercial and technical drivers for vertical farming
Make or buy? Commercial and technical drivers for vertical farming
 
Forecasting the emerging trends and technologies shaping the industry
Forecasting the emerging trends and technologies shaping the industryForecasting the emerging trends and technologies shaping the industry
Forecasting the emerging trends and technologies shaping the industry
 
Cool presentation for slide share
Cool presentation for slide shareCool presentation for slide share
Cool presentation for slide share
 
Bluetooth Classic - dead or alive?
Bluetooth Classic - dead or alive?Bluetooth Classic - dead or alive?
Bluetooth Classic - dead or alive?
 
Encapsulation for industrial applications
Encapsulation for industrial applicationsEncapsulation for industrial applications
Encapsulation for industrial applications
 
Last mile aerial delivery - will the dream become a reality?
Last mile aerial delivery - will the dream become a reality?Last mile aerial delivery - will the dream become a reality?
Last mile aerial delivery - will the dream become a reality?
 
Beyond the visible - real time crop monitoring at real world speeds
Beyond the visible - real time crop monitoring at real world speedsBeyond the visible - real time crop monitoring at real world speeds
Beyond the visible - real time crop monitoring at real world speeds
 
Bluetooth Smart: Connecting Medical Devices to Smart Phones
Bluetooth Smart: Connecting Medical Devices to Smart PhonesBluetooth Smart: Connecting Medical Devices to Smart Phones
Bluetooth Smart: Connecting Medical Devices to Smart Phones
 
Cambridge Consultants Innovation Day 2012: Consumer healthcare and healthy co...
Cambridge Consultants Innovation Day 2012: Consumer healthcare and healthy co...Cambridge Consultants Innovation Day 2012: Consumer healthcare and healthy co...
Cambridge Consultants Innovation Day 2012: Consumer healthcare and healthy co...
 
Cambridge Consultants Innovation Day 2012: Mapping a bright future
Cambridge Consultants Innovation Day 2012: Mapping a bright futureCambridge Consultants Innovation Day 2012: Mapping a bright future
Cambridge Consultants Innovation Day 2012: Mapping a bright future
 
Cambridge Consultants Innovation Day 2012: Innovating for consumers in emergi...
Cambridge Consultants Innovation Day 2012: Innovating for consumers in emergi...Cambridge Consultants Innovation Day 2012: Innovating for consumers in emergi...
Cambridge Consultants Innovation Day 2012: Innovating for consumers in emergi...
 
Cambridge Consultants Innovation Day 2012: Connected machines in a digital ec...
Cambridge Consultants Innovation Day 2012: Connected machines in a digital ec...Cambridge Consultants Innovation Day 2012: Connected machines in a digital ec...
Cambridge Consultants Innovation Day 2012: Connected machines in a digital ec...
 

Recently uploaded

Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptxLBM Solutions
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024The Digital Insurer
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024BookNet Canada
 
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024BookNet Canada
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr BaganFwdays
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupFlorian Wilhelm
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024Scott Keck-Warren
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Wonjun Hwang
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 

Recently uploaded (20)

Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptx
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food Manufacturing
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
 
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project Setup
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024
 
Hot Sexy call girls in Panjabi Bagh 🔝 9953056974 🔝 Delhi escort Service
Hot Sexy call girls in Panjabi Bagh 🔝 9953056974 🔝 Delhi escort ServiceHot Sexy call girls in Panjabi Bagh 🔝 9953056974 🔝 Delhi escort Service
Hot Sexy call girls in Panjabi Bagh 🔝 9953056974 🔝 Delhi escort Service
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 

Robots - Getting out of factories and into fields

  • 1. 17 July 2015 Industrial Automation 9th June Chris Roberts
  • 2. 17 July 2015 2 Background
  • 3. 17 July 2015 3 Overview of Cambridge Consultants We are a world leader in technology and product innovation  400 engineers, scientists, designers and consultants working from our offices in UK and US  For clients world wide, we – develop breakthrough products & systems – create and license intellectual property – provide business consulting in technology critical issues  70% of our work is repeat business – we become trusted partners for our clients Cambridge MA Cambridge UK Singapore
  • 4. 17 July 2015 4 Agenda What’s the problem we’re trying to solve here?  Robots are excellent at – Repetitive tasks – Hard objects – Exact dimensions – Controlled environments
  • 5. 17 July 2015 5 Agenda What’s the problem we’re trying to solve here?  Robots are NOT excellent at – Tasks that change – Objects that can’t be gripped firmly – Objects with varying sizes and shapes – Environments that change
  • 6. 17 July 2015 6 Future world of work research– 2020 to 2030 Will robots steal jobs? Mature territories Aging workforce, receding retirement age, expecting better jobs Networked, integrated warehouse systems Growing Territories Highly-mobile workforce with high expectations of a good work-life balance Increased uptake of control and automation Emerging Territories High turnover of young staff with low technical skills Remote monitoring of warehouses
  • 7. 17 July 2015 7 Robotics and machine vision Science vs Engineering
  • 8. 17 July 2015 8 Robotics case study – Amazon picking challenge “ The winning design was capable of picking up 12 objects in 20 minutes ”
  • 9. 17 July 2015 9 Machine vision case study – ArcAid  Measures the arc of the throw in real time  Offers rating, advice
  • 10. 17 July 2015 10 Machine vision case study – ArcAid
  • 11. 17 July 2015 11 Cambridge Consultants Robotics Project
  • 12. 17 July 2015 12 Agenda Why are we doing this now?  Robotics experience  Low cost sensors and powerful image processing algorithms are available  Embedded processing power
  • 13. 17 July 2015 13 So, what’s the challenge?
  • 14. 17 July 2015 14 There are three main technical challenges to picking fruit or vegetables in a warehouse or field:  Grippers / actuators need to cope with softer objects  Algorithms and control systems that can cope without exact models of the environment and objects  Robots that can interact safely with humans This project focusses on the first two challenges
  • 15. 17 July 2015 15 Gripper
  • 16. 17 July 2015 16 Custom gripper design
  • 17. 17 July 2015 17 Custom gripper design
  • 18. 17 July 2015 18 Custom gripper design
  • 19. 17 July 2015 19 Vision Processing
  • 20. 17 July 2015 20 Vision system  Determine which object is on top of a pile of similar objects  Real time processing of the images and depth maps  No precise description of the object exists  The objects are similar but not identical  Low cost, commodity hardware  Determine where to place gripper
  • 21. 17 July 2015 21 Vision system  Load Objects Step  Process Images Step
  • 22. 17 July 2015 22 Vision system 20 40 60 80 100 120 140 160 180 200 20 40 60 80 100 120 140 160 180 20 40 60 80 100 120 140 160 180 200 20 40 60 80 100 120 140 160 180  Process Objects Step
  • 23. 17 July 2015 23 Vision system  Select Objects Step
  • 24. 17 July 2015 24 Conclusions
  • 25. 17 July 2015 25 Getting robots into the field?  Not quite yet – intermediate step  The proof of concept stage is not the hard one  Engineering is as important as the science
  • 26. 17 July 2015 26 Getting robots into the field? Embedded processor RTOS Vision Driver Image Processing Object Detection Robot Movement Gripper Vision Sensor Object Sensor Driver Low -level Robot control Vacuum Control Gripper Control Robot Arm Vacuum Pump and Valves Depth Sensor
  • 27. 17 July 2015 27 Getting robots into the field?  Is it worth it?  For some applications it will be – but there needs to be a business case  Development will be expensive
  • 28. 17 July 2015 Cambridge Consultants Ltd Science Park, Milton Road Cambridge CB4 0DW England Cambridge Consultants Inc 101 Main Street Cambridge MA 02142 USA Tel: +44 (0)1223 420024 Fax: +44 (0)1223 423373 Tel: +1 617 532 4700 Fax: +1 617 532 4747 Registered No. 1036296 England Cambridge Consultants is part of the Altran group, a global leader in Innovation. www.Altran.com info@CambridgeConsultants.com www.CambridgeConsultants.com

Editor's Notes

  1. I’m a physicist by background – I started off in the space industry before moving to product design Experience in chip design – lead multiple mixed signal ASIC developments Now system lead, interested in low power designs Commercial applications of VR Robotics, machine vision
  2. Robot technology has been around for a long time, and robots are amazingly good at doing the same thing over and over again. Typically used in factory environments Hard objects, exact dimensions, known locations
  3. Where robots traditionally struggle is doing not quite the same thing, over and over again Fields, shopping (e.g. Amazon picking challenge) Softer objects, no CAD model, no exact locations
  4. Why try to replace humans? Do they even want to be replaced? Are we stealing jobs? Future world of work 2020-2030 research. examine factors that will influence the way work is done in the manufacturing workplace of the future, and in the associated logistics operations Divided into three territories Mature, e.g. USA, Czech Republic Growing, e.g. India, Botswana Emerging, e.g. Tanzania, Honduras Principle time line is 2020-2030 Mature: see high levels of automation in the manufacturing sector in 2020, but there will be issues with an ageing workforce Growing: will see rapid technology advancements and pressure on employers due to rise in workforce expectations Emerging: Not yet ready for automation But in both the mature and growing territories people will be starting to reject the kind of jobs that can be done by robots.
  5. There are lots of projects that from a technical point of view are very impressive. The Amazon picking challenge – a robot that can pick any object off the shelf without damaging it – amazing. But if you take a step back and look what the end result was – no where near as good as a human. It’s a HARD technical problem, and the end result was not as good as a human Compare this to the Kiva robots that move the shelves around – technically EASY, but the engineering was HARD
  6. This is a demo we did for CES last year It was part of elite sports training campaign You took five free throws at the basket, and the app rated your throw in real time and offered training advice Nowhere near as hard as the Amazon picking challenge
  7. But the image processing was actually pretty easy – spotting a solid coloured circle in an image is a simple algorithm And then taking away the heads , signs and other objects that didn’t move like a ball was also easy This was an EASY technical problem but the ENGINEERING was HARD – getting it to work in the CES environment
  8. There are some micro influences that are pushing us to do this now Robotics experience We’ve done some really clever things with robots that we can’t talk publicly about yet… …but this is something we can Many projects recently have hinged on combining Low cost sensors with some really clever algorithms running on increasingly capable commodity hardware.
  9. Cambridge Consultants has been working on a way of getting robots to determine the location of fruit or vegetables and pick them up
  10. Algorithms and control systems that can cope without exact models of the environment and objects Real time processing Object sensing and categorisation Adaptive control Why is it hard? The science is difficult but not impossible It’s the engineering that’s tricky
  11. Surveyed existing technology Fixing on fruit and vegetables gives us a limited space to explore don’t have to cope with everything Multiple bellows approach object from all sides Control system only applies suction where there is a seal
  12. The machine vision processing begins with an optical image and several depth maps generated through structured light Load Objects Step Import images and depth map Pre-processing Process Images Step Selection of area of interest Cropping and scaling
  13. Process Objects Step Troughs between objects determined Objects segmented and numbered This is where the hardest part is – working out which potato is which
  14. Orders objects by height Determines where to place gripper
  15. IF it’s going to succeed in the field, it needs to be robustly engineered Not just a bunch of raspberry pis and image processing running on matlab Low cost, commodity hardware Unnecessary links removed A single processing engine – custom silicon if necessary