SlideShare a Scribd company logo
1 of 13
Download to read offline
SMART CABS:
                                                                              MACHINES THAT
                                                                              KNOW THEIR
                                                                              DRIVERS
                                                                              Rod Walsh, Petri Murtomaki, and
                                                                              Kimmo Vänni
                                                                              TAMK
version

0.1
           date

           15.03.2012
                        author

                        RW & KV
                                    details

                                    Created & first ideas
                                                                              Demola InnoSummer 2012
0.2        16.03.2012   Rod Walsh   Minor improvements
0.3        02.05.2012   Rod Walsh   Filled out the “complete story”




      © TAMK, 2012. ALL RIGHTS RESERVED.                              TAMK CONFIDENTIAL.                        1
COMING UP IN THIS SLIDE SET…


        Why:                   Better Performance in Forestry
        What:                  The Human Touch
        How:                   The Demo
        Where:                 The Big Idea
        Approach:              Approach




© TAMK, 2012. ALL RIGHTS RESERVED.             TAMK CONFIDENTIAL.   2
BETTER PERFORMANCE IN FORESTRY
        The commercial performance of large human-operated machines is
           largely determined by the performance of the human operator
        Today, human operator performance is largely driven by hard external
           factors, such as training, experience and attitude
        Dynamic factors are “left to care for themselves”: such as tiredness,
           alertness, attentiveness, happiness, etc.
        But we want to use technology and human-insight to monitor these soft
           internal factors
        And improve working life, long-term health and commercial productivity




© TAMK, 2012. ALL RIGHTS RESERVED.      TAMK CONFIDENTIAL.                        3
THE HUMAN TOUCH                                                     non-contact sensing


 We will take a look at the emotional state-of-mind of
  operators using face, sound and posture monitoring
  technology with pattern recognition                                                               Psychology
                                                                                                   & processing
 And use our knowledge of these soft internal factors for
  improvements:                                                             state of mind
      Happier and lower-stress work (short and long term benefit for the
        employee)
      Better productivity (short and long term benefit for the employer)

 By:
      Dynamically modifying the working environment for the better
        (short term)
      Identifying positive patterns of emotion affect on human                     Simple changes
        performance & motivation, and then matching practices, assignments          • Music, lighting, airflow, …
        and environments the patterns (long-term)




                                       Pattern                Working
                                     recognition              practices

© TAMK, 2012. ALL RIGHTS RESERVED.                 TAMK CONFIDENTIAL.                                  4
Examples of “state of mind”
THE DEMO                                                                                  • Tiredness
                                                                                          • Boredom
                                                                                          • Willingness to work
                                                                                          • Fear/anxiety
 Multiple HD webcams, microphones and PrimeSense IR sensors (e.g.                        • Happiness
   Kinect) will be arranged to monitor a human “operator” (non-contact
   sensing)                                                            Examples of corrective action:
      (For versatility, an “office desk operator” setup is needed. The team may take     •   Encouragement
         physical forestry machine mock-ups and closeness-to-reality to higher levels.)   •   Stimulation
 A set of “states of mind” that are relevant to machine operator                         •   Pause/end of task
   performance and wellbeing will be selected                                             •   Verify the measurement
      Quickly selected emotions at first (for rapid development) & then iterated         Examples of Job improvements:
 Sensor signals are classified for the “states of mind”                                  • Productivity
    Classifier(s) will be “trained” and tested. Training and testing will begin with
                                                                                               • Volume
      “acted emotions” and tightly iterated between the pattern recognition and                • Errors
      the pyschology/emotional model.                                                     • Motivation for the job
 Offline: all sensor and analytics data will be logged, to allow discovery               • Intervention before
  of longer-term patterns (such as time of day patterns)                                     problems become critical
 Real-time: The instantiations state-of-mind is matched against a “task
  model” and need for corrective action (on the operator) is
  calculated
 As determined, corrective action is taken to change the operator’s
  environment
      The effects and affects are logged to determine whether the action succeeded
      (The “office desk simulator” can be a PC display simulation, or better…)


SEE NEXT SLIDE FOR VISUAL DESCRIPTION
© TAMK, 2012. ALL RIGHTS RESERVED.                 TAMK CONFIDENTIAL.                                             5
THE DEMO                                               Database:                non-contact sensing:
                                                       state of mind log        video, image, audio
                              Pattern                  sensor logs
                            recognition
                                                                           logged
                                                        logged offline

                                                                             real-time
                                                                                                            7/10
                                                                                                           capability

                                                        state of mind
                                                         estimation

                                       ~7/10
                                       capability

                                                    Match
                                                    with
                                                     task                  Simulate simple changes
                                        8/10                               • Music, lighting, airflow, …
                                       minimum




  © TAMK, 2012. ALL RIGHTS RESERVED.                   TAMK CONFIDENTIAL.                                    6
THE BIG PICTURE
        For the long-term benefits, the data can be used to change the design of
           working environments and practices, so…
        The demo would be integrated to a larger system (see next slide)


        Existing telematics data from the forestry machines can introduced to
           the common database and analyzed for patterns between operator
           state of mind and machine behavior (for further insights and causalities)


        This is beyond what the team needs to do!
              The team’s innovation and excitement decide what is done beyond the core demo




© TAMK, 2012. ALL RIGHTS RESERVED.         TAMK CONFIDENTIAL.                                  7
Human impact
                                                       Database:
                                                                           THE BIG PICTURE
   on work
   quality &                                           telematics log
productivity &                                         state of mind log
   machine                                             sensor logs
 performance
                                                                                                state of mind
 Machine +         Logging telematics
environment         (exists already)
 impact on                                                                                            capability
   human
  operator



                                       capability



                                                    Match
                                                                                                Improvements
                                       required
                                                                            corrective action




  © TAMK, 2012. ALL RIGHTS RESERVED.                   TAMK CONFIDENTIAL.                               8
APPROACH
 In theory, the team is free to adopt any approach that:
       Works well, looks great and receives “ooh” and “wow” sounds
       Fits the objectives
       Is reusable, extendable and portable (as a whole and as components)

 Meeting these needs in one go is near impossible, so iteration, communication
    and sharing are critical – and at high speed!
 In practice, the support team has some useful experience and advice:
       Short design, implementation and demo iterations are the safest and coolest
       Stick to technologies which are cross-platform and open (when possible):
             E.g. HTML5, OpenNI, Published solutions, etc. as applicable

             We will supply USB webcams (inc. microphones) and PrimeSense IR sensors

             Code should be runnable on Mac/Win/Linux (Ubuntu is our favorite Linux)

       We will workshop together to best use the team’s and the support team’s knowledge




© TAMK, 2012. ALL RIGHTS RESERVED.                TAMK CONFIDENTIAL.                        9
Some support slides

…
Together with another awesome project,

 SMART CAB +                                                               we could close the loop on emotional
                                                                            feedback (possible project extension)

 AFFECTIVE ROBOTS

                                                                                                state of mind
                                               state of mind
                    Goal                        estimation
                                Match




                     Emotive
“corrective”         commands
action using and     like:
emotionally-savvy    • be happy
avatar               • welcome
                                                                                      1. Perform the emotion
                     • Reject
                     • cry                                                            2. Perform for the emotion
                                             What setting or stage would unlock,
                                                 actual robot virtual robot           3. Read/write emotion?
                                              emphasize or inhibit which affects?
     body
             face
      Full




                            modeled human-like emotion



© TAMK, 2012. ALL RIGHTS RESERVED.               TAMK CONFIDENTIAL.                                       11
Human impact                                                                    non-contact sensing:
   on work                                             Database:
                                                       telematics log           video, image, audio
   quality &
productivity &                Pattern                  state of mind log
   machine                  recognition                sensor logs
                                                                           logged
 performance
                                                        logged offline
                                                                                                           “state of mind”
 Machine +         Logging telematics                                        real-time
environment         (exists already)
 impact on
                                                                                                                   7/10
                                                                                                                  capability
   human
  operator                                              state of mind
                                                         estimation

                                       ~7/10
                                       capability

                                                    Match
                                                    with
                                                     task                  Simulate simple changes         Job improvements
                                        8/10                               • Music, lighting, airflow, …
                                       minimum
                                                                                corrective action




  © TAMK, 2012. ALL RIGHTS RESERVED.                   TAMK CONFIDENTIAL.                                           12
SIMPLE ONE-SLIDER

  Design of
 practices &
environment




                     telematics




 © TAMK, 2012. ALL RIGHTS RESERVED.   TAMK CONFIDENTIAL.   13

More Related Content

Viewers also liked

Howtocreateaneffective group2morningb
Howtocreateaneffective group2morningbHowtocreateaneffective group2morningb
Howtocreateaneffective group2morningbWagner Junior
 
Demola deep avatars simple robots 20130121
Demola deep avatars simple robots 20130121Demola deep avatars simple robots 20130121
Demola deep avatars simple robots 20130121Rod Walsh
 
Reflectivewritingandrevision group2morningb
Reflectivewritingandrevision group2morningbReflectivewritingandrevision group2morningb
Reflectivewritingandrevision group2morningbWagner Junior
 
Delhi draft industrialpolicy
Delhi draft industrialpolicyDelhi draft industrialpolicy
Delhi draft industrialpolicyIndu Gupta
 
Demola mind reader 20120903
Demola mind reader 20120903Demola mind reader 20120903
Demola mind reader 20120903Rod Walsh
 
Reflectivewritingandrevision group2morningb
Reflectivewritingandrevision group2morningbReflectivewritingandrevision group2morningb
Reflectivewritingandrevision group2morningbWagner Junior
 
TamkUxdSocRob_20120904
TamkUxdSocRob_20120904TamkUxdSocRob_20120904
TamkUxdSocRob_20120904Rod Walsh
 
Demola train one train all 20120903
Demola train one train all 20120903Demola train one train all 20120903
Demola train one train all 20120903Rod Walsh
 
Creative teaching 3rd august
Creative teaching 3rd augustCreative teaching 3rd august
Creative teaching 3rd augustIndu Gupta
 
Social Robotics for Assisted Living
Social Robotics for Assisted LivingSocial Robotics for Assisted Living
Social Robotics for Assisted LivingRod Walsh
 
Reflectivewritingandrevision group2morningb
Reflectivewritingandrevision group2morningbReflectivewritingandrevision group2morningb
Reflectivewritingandrevision group2morningbWagner Junior
 
二代U盾快速使用指南
二代U盾快速使用指南二代U盾快速使用指南
二代U盾快速使用指南liulizhiri
 

Viewers also liked (16)

Howtocreateaneffective group2morningb
Howtocreateaneffective group2morningbHowtocreateaneffective group2morningb
Howtocreateaneffective group2morningb
 
Demola deep avatars simple robots 20130121
Demola deep avatars simple robots 20130121Demola deep avatars simple robots 20130121
Demola deep avatars simple robots 20130121
 
Reflectivewritingandrevision group2morningb
Reflectivewritingandrevision group2morningbReflectivewritingandrevision group2morningb
Reflectivewritingandrevision group2morningb
 
Delhi draft industrialpolicy
Delhi draft industrialpolicyDelhi draft industrialpolicy
Delhi draft industrialpolicy
 
Demola mind reader 20120903
Demola mind reader 20120903Demola mind reader 20120903
Demola mind reader 20120903
 
Reflectivewritingandrevision group2morningb
Reflectivewritingandrevision group2morningbReflectivewritingandrevision group2morningb
Reflectivewritingandrevision group2morningb
 
TamkUxdSocRob_20120904
TamkUxdSocRob_20120904TamkUxdSocRob_20120904
TamkUxdSocRob_20120904
 
Demola train one train all 20120903
Demola train one train all 20120903Demola train one train all 20120903
Demola train one train all 20120903
 
Bizcraft
BizcraftBizcraft
Bizcraft
 
Ppm5
Ppm5Ppm5
Ppm5
 
Creative teaching 3rd august
Creative teaching 3rd augustCreative teaching 3rd august
Creative teaching 3rd august
 
Social Robotics for Assisted Living
Social Robotics for Assisted LivingSocial Robotics for Assisted Living
Social Robotics for Assisted Living
 
Reflectivewritingandrevision group2morningb
Reflectivewritingandrevision group2morningbReflectivewritingandrevision group2morningb
Reflectivewritingandrevision group2morningb
 
Presentasjon delicious
Presentasjon deliciousPresentasjon delicious
Presentasjon delicious
 
二代U盾快速使用指南
二代U盾快速使用指南二代U盾快速使用指南
二代U盾快速使用指南
 
Analisis soalan upsr bm
Analisis soalan upsr bmAnalisis soalan upsr bm
Analisis soalan upsr bm
 

Similar to Demola smart cabs_20120502

Similar to Demola smart cabs_20120502 (20)

Hci and psychology
Hci and psychologyHci and psychology
Hci and psychology
 
Samples 3 Print
Samples 3 PrintSamples 3 Print
Samples 3 Print
 
120906 inchron rhapsody enlightenment
120906 inchron rhapsody enlightenment120906 inchron rhapsody enlightenment
120906 inchron rhapsody enlightenment
 
Introduction To Biometrics
Introduction To BiometricsIntroduction To Biometrics
Introduction To Biometrics
 
IPM_E_3.2.12
IPM_E_3.2.12IPM_E_3.2.12
IPM_E_3.2.12
 
IPM_E_8.2.2012
IPM_E_8.2.2012IPM_E_8.2.2012
IPM_E_8.2.2012
 
IPM_E_8.2.2012
IPM_E_8.2.2012IPM_E_8.2.2012
IPM_E_8.2.2012
 
IPM_E_8.2.2012
IPM_E_8.2.2012IPM_E_8.2.2012
IPM_E_8.2.2012
 
IRM_E_19.3.12
IRM_E_19.3.12IRM_E_19.3.12
IRM_E_19.3.12
 
How Do Our Clients Use CONOPS?
How Do Our Clients Use CONOPS?How Do Our Clients Use CONOPS?
How Do Our Clients Use CONOPS?
 
HRCM_E_2FEB2012
HRCM_E_2FEB2012HRCM_E_2FEB2012
HRCM_E_2FEB2012
 
IRM_E_25.2.12
IRM_E_25.2.12IRM_E_25.2.12
IRM_E_25.2.12
 
Quantum Lab White Paper
Quantum Lab White PaperQuantum Lab White Paper
Quantum Lab White Paper
 
Flash performance tuning (EN)
Flash performance tuning (EN)Flash performance tuning (EN)
Flash performance tuning (EN)
 
IEM_E_13.2.12
IEM_E_13.2.12IEM_E_13.2.12
IEM_E_13.2.12
 
Intro web 2.0
Intro web 2.0Intro web 2.0
Intro web 2.0
 
IRM_E_17.3.12
IRM_E_17.3.12IRM_E_17.3.12
IRM_E_17.3.12
 
eTrax, Staff Monitoring System
eTrax, Staff Monitoring SystemeTrax, Staff Monitoring System
eTrax, Staff Monitoring System
 
Kohlbecker Low Latency Combined Eye And Head Tracking System For Teleoperatin...
Kohlbecker Low Latency Combined Eye And Head Tracking System For Teleoperatin...Kohlbecker Low Latency Combined Eye And Head Tracking System For Teleoperatin...
Kohlbecker Low Latency Combined Eye And Head Tracking System For Teleoperatin...
 
IRM_E_12.03.12
IRM_E_12.03.12IRM_E_12.03.12
IRM_E_12.03.12
 

Recently uploaded

Painted Grey Ware.pptx, PGW Culture of India
Painted Grey Ware.pptx, PGW Culture of IndiaPainted Grey Ware.pptx, PGW Culture of India
Painted Grey Ware.pptx, PGW Culture of IndiaVirag Sontakke
 
Blooming Together_ Growing a Community Garden Worksheet.docx
Blooming Together_ Growing a Community Garden Worksheet.docxBlooming Together_ Growing a Community Garden Worksheet.docx
Blooming Together_ Growing a Community Garden Worksheet.docxUnboundStockton
 
CARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxCARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxGaneshChakor2
 
Hybridoma Technology ( Production , Purification , and Application )
Hybridoma Technology  ( Production , Purification , and Application  ) Hybridoma Technology  ( Production , Purification , and Application  )
Hybridoma Technology ( Production , Purification , and Application ) Sakshi Ghasle
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)eniolaolutunde
 
How to Configure Email Server in Odoo 17
How to Configure Email Server in Odoo 17How to Configure Email Server in Odoo 17
How to Configure Email Server in Odoo 17Celine George
 
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdfBASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdfSoniaTolstoy
 
Alper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentAlper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentInMediaRes1
 
internship ppt on smartinternz platform as salesforce developer
internship ppt on smartinternz platform as salesforce developerinternship ppt on smartinternz platform as salesforce developer
internship ppt on smartinternz platform as salesforce developerunnathinaik
 
Class 11 Legal Studies Ch-1 Concept of State .pdf
Class 11 Legal Studies Ch-1 Concept of State .pdfClass 11 Legal Studies Ch-1 Concept of State .pdf
Class 11 Legal Studies Ch-1 Concept of State .pdfakmcokerachita
 
Final demo Grade 9 for demo Plan dessert.pptx
Final demo Grade 9 for demo Plan dessert.pptxFinal demo Grade 9 for demo Plan dessert.pptx
Final demo Grade 9 for demo Plan dessert.pptxAvyJaneVismanos
 
Crayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon ACrayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon AUnboundStockton
 
The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13Steve Thomason
 
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions  for the students and aspirants of Chemistry12th.pptxOrganic Name Reactions  for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions for the students and aspirants of Chemistry12th.pptxVS Mahajan Coaching Centre
 
Computed Fields and api Depends in the Odoo 17
Computed Fields and api Depends in the Odoo 17Computed Fields and api Depends in the Odoo 17
Computed Fields and api Depends in the Odoo 17Celine George
 
Proudly South Africa powerpoint Thorisha.pptx
Proudly South Africa powerpoint Thorisha.pptxProudly South Africa powerpoint Thorisha.pptx
Proudly South Africa powerpoint Thorisha.pptxthorishapillay1
 
A Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformA Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformChameera Dedduwage
 
Employee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxEmployee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxNirmalaLoungPoorunde1
 

Recently uploaded (20)

Painted Grey Ware.pptx, PGW Culture of India
Painted Grey Ware.pptx, PGW Culture of IndiaPainted Grey Ware.pptx, PGW Culture of India
Painted Grey Ware.pptx, PGW Culture of India
 
Blooming Together_ Growing a Community Garden Worksheet.docx
Blooming Together_ Growing a Community Garden Worksheet.docxBlooming Together_ Growing a Community Garden Worksheet.docx
Blooming Together_ Growing a Community Garden Worksheet.docx
 
CARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxCARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptx
 
Hybridoma Technology ( Production , Purification , and Application )
Hybridoma Technology  ( Production , Purification , and Application  ) Hybridoma Technology  ( Production , Purification , and Application  )
Hybridoma Technology ( Production , Purification , and Application )
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)
 
How to Configure Email Server in Odoo 17
How to Configure Email Server in Odoo 17How to Configure Email Server in Odoo 17
How to Configure Email Server in Odoo 17
 
9953330565 Low Rate Call Girls In Rohini Delhi NCR
9953330565 Low Rate Call Girls In Rohini  Delhi NCR9953330565 Low Rate Call Girls In Rohini  Delhi NCR
9953330565 Low Rate Call Girls In Rohini Delhi NCR
 
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdfBASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
 
Alper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentAlper Gobel In Media Res Media Component
Alper Gobel In Media Res Media Component
 
internship ppt on smartinternz platform as salesforce developer
internship ppt on smartinternz platform as salesforce developerinternship ppt on smartinternz platform as salesforce developer
internship ppt on smartinternz platform as salesforce developer
 
Class 11 Legal Studies Ch-1 Concept of State .pdf
Class 11 Legal Studies Ch-1 Concept of State .pdfClass 11 Legal Studies Ch-1 Concept of State .pdf
Class 11 Legal Studies Ch-1 Concept of State .pdf
 
Final demo Grade 9 for demo Plan dessert.pptx
Final demo Grade 9 for demo Plan dessert.pptxFinal demo Grade 9 for demo Plan dessert.pptx
Final demo Grade 9 for demo Plan dessert.pptx
 
Crayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon ACrayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon A
 
The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13
 
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions  for the students and aspirants of Chemistry12th.pptxOrganic Name Reactions  for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
 
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
 
Computed Fields and api Depends in the Odoo 17
Computed Fields and api Depends in the Odoo 17Computed Fields and api Depends in the Odoo 17
Computed Fields and api Depends in the Odoo 17
 
Proudly South Africa powerpoint Thorisha.pptx
Proudly South Africa powerpoint Thorisha.pptxProudly South Africa powerpoint Thorisha.pptx
Proudly South Africa powerpoint Thorisha.pptx
 
A Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformA Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy Reform
 
Employee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxEmployee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptx
 

Demola smart cabs_20120502

  • 1. SMART CABS: MACHINES THAT KNOW THEIR DRIVERS Rod Walsh, Petri Murtomaki, and Kimmo Vänni TAMK version 0.1 date 15.03.2012 author RW & KV details Created & first ideas Demola InnoSummer 2012 0.2 16.03.2012 Rod Walsh Minor improvements 0.3 02.05.2012 Rod Walsh Filled out the “complete story” © TAMK, 2012. ALL RIGHTS RESERVED. TAMK CONFIDENTIAL. 1
  • 2. COMING UP IN THIS SLIDE SET…  Why: Better Performance in Forestry  What: The Human Touch  How: The Demo  Where: The Big Idea  Approach: Approach © TAMK, 2012. ALL RIGHTS RESERVED. TAMK CONFIDENTIAL. 2
  • 3. BETTER PERFORMANCE IN FORESTRY  The commercial performance of large human-operated machines is largely determined by the performance of the human operator  Today, human operator performance is largely driven by hard external factors, such as training, experience and attitude  Dynamic factors are “left to care for themselves”: such as tiredness, alertness, attentiveness, happiness, etc.  But we want to use technology and human-insight to monitor these soft internal factors  And improve working life, long-term health and commercial productivity © TAMK, 2012. ALL RIGHTS RESERVED. TAMK CONFIDENTIAL. 3
  • 4. THE HUMAN TOUCH non-contact sensing  We will take a look at the emotional state-of-mind of operators using face, sound and posture monitoring technology with pattern recognition Psychology & processing  And use our knowledge of these soft internal factors for improvements: state of mind  Happier and lower-stress work (short and long term benefit for the employee)  Better productivity (short and long term benefit for the employer)  By:  Dynamically modifying the working environment for the better (short term)  Identifying positive patterns of emotion affect on human Simple changes performance & motivation, and then matching practices, assignments • Music, lighting, airflow, … and environments the patterns (long-term) Pattern Working recognition practices © TAMK, 2012. ALL RIGHTS RESERVED. TAMK CONFIDENTIAL. 4
  • 5. Examples of “state of mind” THE DEMO • Tiredness • Boredom • Willingness to work • Fear/anxiety  Multiple HD webcams, microphones and PrimeSense IR sensors (e.g. • Happiness Kinect) will be arranged to monitor a human “operator” (non-contact sensing) Examples of corrective action:  (For versatility, an “office desk operator” setup is needed. The team may take • Encouragement physical forestry machine mock-ups and closeness-to-reality to higher levels.) • Stimulation  A set of “states of mind” that are relevant to machine operator • Pause/end of task performance and wellbeing will be selected • Verify the measurement  Quickly selected emotions at first (for rapid development) & then iterated Examples of Job improvements:  Sensor signals are classified for the “states of mind” • Productivity  Classifier(s) will be “trained” and tested. Training and testing will begin with • Volume “acted emotions” and tightly iterated between the pattern recognition and • Errors the pyschology/emotional model. • Motivation for the job  Offline: all sensor and analytics data will be logged, to allow discovery • Intervention before of longer-term patterns (such as time of day patterns) problems become critical  Real-time: The instantiations state-of-mind is matched against a “task model” and need for corrective action (on the operator) is calculated  As determined, corrective action is taken to change the operator’s environment  The effects and affects are logged to determine whether the action succeeded  (The “office desk simulator” can be a PC display simulation, or better…) SEE NEXT SLIDE FOR VISUAL DESCRIPTION © TAMK, 2012. ALL RIGHTS RESERVED. TAMK CONFIDENTIAL. 5
  • 6. THE DEMO Database: non-contact sensing: state of mind log video, image, audio Pattern sensor logs recognition logged logged offline real-time 7/10 capability state of mind estimation ~7/10 capability Match with task Simulate simple changes 8/10 • Music, lighting, airflow, … minimum © TAMK, 2012. ALL RIGHTS RESERVED. TAMK CONFIDENTIAL. 6
  • 7. THE BIG PICTURE  For the long-term benefits, the data can be used to change the design of working environments and practices, so…  The demo would be integrated to a larger system (see next slide)  Existing telematics data from the forestry machines can introduced to the common database and analyzed for patterns between operator state of mind and machine behavior (for further insights and causalities)  This is beyond what the team needs to do!  The team’s innovation and excitement decide what is done beyond the core demo © TAMK, 2012. ALL RIGHTS RESERVED. TAMK CONFIDENTIAL. 7
  • 8. Human impact Database: THE BIG PICTURE on work quality & telematics log productivity & state of mind log machine sensor logs performance state of mind Machine + Logging telematics environment (exists already) impact on capability human operator capability Match Improvements required corrective action © TAMK, 2012. ALL RIGHTS RESERVED. TAMK CONFIDENTIAL. 8
  • 9. APPROACH  In theory, the team is free to adopt any approach that:  Works well, looks great and receives “ooh” and “wow” sounds  Fits the objectives  Is reusable, extendable and portable (as a whole and as components)  Meeting these needs in one go is near impossible, so iteration, communication and sharing are critical – and at high speed!  In practice, the support team has some useful experience and advice:  Short design, implementation and demo iterations are the safest and coolest  Stick to technologies which are cross-platform and open (when possible):  E.g. HTML5, OpenNI, Published solutions, etc. as applicable  We will supply USB webcams (inc. microphones) and PrimeSense IR sensors  Code should be runnable on Mac/Win/Linux (Ubuntu is our favorite Linux)  We will workshop together to best use the team’s and the support team’s knowledge © TAMK, 2012. ALL RIGHTS RESERVED. TAMK CONFIDENTIAL. 9
  • 11. Together with another awesome project, SMART CAB + we could close the loop on emotional feedback (possible project extension) AFFECTIVE ROBOTS state of mind state of mind Goal estimation Match Emotive “corrective” commands action using and like: emotionally-savvy • be happy avatar • welcome 1. Perform the emotion • Reject • cry 2. Perform for the emotion What setting or stage would unlock, actual robot virtual robot 3. Read/write emotion? emphasize or inhibit which affects? body face Full modeled human-like emotion © TAMK, 2012. ALL RIGHTS RESERVED. TAMK CONFIDENTIAL. 11
  • 12. Human impact non-contact sensing: on work Database: telematics log video, image, audio quality & productivity & Pattern state of mind log machine recognition sensor logs logged performance logged offline “state of mind” Machine + Logging telematics real-time environment (exists already) impact on 7/10 capability human operator state of mind estimation ~7/10 capability Match with task Simulate simple changes Job improvements 8/10 • Music, lighting, airflow, … minimum corrective action © TAMK, 2012. ALL RIGHTS RESERVED. TAMK CONFIDENTIAL. 12
  • 13. SIMPLE ONE-SLIDER Design of practices & environment telematics © TAMK, 2012. ALL RIGHTS RESERVED. TAMK CONFIDENTIAL. 13