SlideShare une entreprise Scribd logo
1  sur  16
Télécharger pour lire hors ligne
Making robots dream to
face open environments
Stéphane Doncieux
What a machine can do
YASKAWA BUSHIDO PROJECT /
industrial robot vs sword master
Deep Blue vs G. Kasparov
1997
Motion Problem resolution
Doncieux, S. (to appear) Creativity: A Driver for Research on Robotics in Open Environments, Intellectica
Performance
Context
Robot A
Robot B
?
??
?
??
Known
Unknown Unknown
How can a robot face a new
environment ?
1. Robustness
2. Learning
3. Development
Manual development1. Robustness
Autonomous development
Learning
2. Learning
Reward
High
Low A
Learning the action to apply in a state to maximize reward.
Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning: An introduction. Cambridge: MIT press.
2. Learning
continuous actions & states
Evaluation
Genotype
Fitness
Random generation
Selection
Variation
8.3
00110100111
Termination
Initial conditionsEvaluation
Genotype
Phenotype
Behavior
Environment
Fitness
Evolutionary Robotics
Mouret, J.B., Bredeche, N. et Doncieux S. La robotique
évolutionniste Pour la science n°87, Avril-Juin 2015
Doncieux, S., Bredeche, N., Mouret, J.-B., & Eiben, A. E.
(2015). Evolutionary Robotics: What, Why, and Where to.
Frontiers in Evolutionary Robotics, doi: 10.3389/frobt.
2015.00004
A
Kober, J., Bagnell, J. a., & Peters, J. (2013). Reinforcement learning in robotics: A survey.
The International Journal of Robotics Research, 32(11), 1238–1274. doi:10.1177/0278364913495721
2. Learning
The representation is critical !
???• Reinforcement Learning: fast but requires an efficient representation
• Evolutionary Robotics: low level representation, but slow…
3. Development
Weng, J. (2004). Developmental robotics : Theory and experiments.
International Journal of Humanoid Robotics, 1(2), 199–236.
Autonomous development
3. Development
Insights from psychology
The importance of redescribing knowledge representations
«  A specifically human way to gain knowledge is for the mind to exploit
internally the information that it has already stored (both innate and
acquired), by redescribing its representations or, more precisely, by
iteratively re-representing in different representational formats what its
internal representations represent » [Karmiloff-Smith 1996]
When to restructure and consolidate knowledge ?
« Sleep consolidates recent memories and, concomitantly, could allow
insight by changing their representational structure. » [Wagner, 2004]
Kick-off meeting DREAM, Paris, 26/01/2015
Deferred Restructuring of Experience
in Autonomous Machines
H2020 FET Proactive « Knowing,
doing, being » 01/2015-12/2018
http://www.robotsthatdream.eu/
https://twitter.com/robotsthatdream
3. Development
Changing representations
Daytime
experience
(large batch)
Daytime
Consolidated knowledge
- task-relevant features
- task contexts
- abstract knowledge
- new motivations
No initial policy
No single task
Motivations:
- curiosity
- satisfying humans
- global mission
Behavior exploration
Knowledge improvement
Knowledge adaptation
Small
batch
Skill
Knowledge validation
Sequence of learning episodes driven by motivations
New situation:
-no reprogramming
-fast adaptation
Knowledge sharing
between robots:
- better generalization
- faster learning
Nighttime
Dream
Collective scale
Individual scale
Knowledge restructuring
Transfer from STM to LTM
Learning 10 to 100
times faster
Generates examples
of behaviours
Discrete actions
and sensors
to consider
Passive analysis
Representation
redescription
2
1
Learning
Direct policy search
(neuroevolution)
Task-agnostic
representations
Slow learning
Limited generalization
3
Learning
Discrete reinforcement
learning
Task-specific
representations
Fast learning
Good generalization
Development: bootstrapping simple manipulation skills
1. Day 1: sensori-motor babbling 2. «Night» Learning to manipulate an object in simulation
3.  Day 2 : Back to reality
Thank you !
Questions ?
stephane.doncieux@upmc.fr
https://twitter.com/SDoncieux
http://people.isir.upmc.fr/doncieux

Contenu connexe

Similaire à Innorobo 2016 Keynote - Making robots dream to face open environments

gpeleg_challenges_robot_manipulation.ppt
gpeleg_challenges_robot_manipulation.pptgpeleg_challenges_robot_manipulation.ppt
gpeleg_challenges_robot_manipulation.ppt
SyamOm
 
How to make harmony with human beings while building AGI?
How to make harmony with human beings while building AGI?How to make harmony with human beings while building AGI?
How to make harmony with human beings while building AGI?
The Whole Brain Architecture Initiative
 
PhD Defence: Leveraging sensing-based interaction for supporting reflection a...
PhD Defence: Leveraging sensing-based interaction for supporting reflection a...PhD Defence: Leveraging sensing-based interaction for supporting reflection a...
PhD Defence: Leveraging sensing-based interaction for supporting reflection a...
Simone Mora
 
Mobile collaborative learning dr.azizah25 oct
Mobile collaborative learning dr.azizah25 octMobile collaborative learning dr.azizah25 oct
Mobile collaborative learning dr.azizah25 oct
Hasnain Zafar
 

Similaire à Innorobo 2016 Keynote - Making robots dream to face open environments (20)

TDLL7353 Lesson 4(ver2)- Artificial Intelligence in Education-The Univeristy ...
TDLL7353 Lesson 4(ver2)- Artificial Intelligence in Education-The Univeristy ...TDLL7353 Lesson 4(ver2)- Artificial Intelligence in Education-The Univeristy ...
TDLL7353 Lesson 4(ver2)- Artificial Intelligence in Education-The Univeristy ...
 
gpeleg_challenges_robot_manipulation.ppt
gpeleg_challenges_robot_manipulation.pptgpeleg_challenges_robot_manipulation.ppt
gpeleg_challenges_robot_manipulation.ppt
 
The university in a box
The university in a boxThe university in a box
The university in a box
 
20210908 jim spohrer naples forum_2021 v1
20210908 jim spohrer naples forum_2021 v120210908 jim spohrer naples forum_2021 v1
20210908 jim spohrer naples forum_2021 v1
 
Cognitive Vision - After the hype
Cognitive Vision - After the hypeCognitive Vision - After the hype
Cognitive Vision - After the hype
 
How to make harmony with human beings while building AGI?
How to make harmony with human beings while building AGI?How to make harmony with human beings while building AGI?
How to make harmony with human beings while building AGI?
 
Machine Learning and Robotic Vision
Machine Learning and Robotic VisionMachine Learning and Robotic Vision
Machine Learning and Robotic Vision
 
Proactive Displays CSCW2008
Proactive Displays CSCW2008Proactive Displays CSCW2008
Proactive Displays CSCW2008
 
120918 cádiz ecer
120918 cádiz ecer120918 cádiz ecer
120918 cádiz ecer
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
 
Introduction to Artificial Intelligence
Introduction to Artificial IntelligenceIntroduction to Artificial Intelligence
Introduction to Artificial Intelligence
 
People As the Conveyor of Knowledge at Agile Vietnam
People As the Conveyor of Knowledge at Agile VietnamPeople As the Conveyor of Knowledge at Agile Vietnam
People As the Conveyor of Knowledge at Agile Vietnam
 
HPAI Class 2 - human aspects and computing systems in ai - 012920
HPAI  Class 2 - human aspects and computing systems in ai - 012920HPAI  Class 2 - human aspects and computing systems in ai - 012920
HPAI Class 2 - human aspects and computing systems in ai - 012920
 
Empirical AI Research
Empirical AI Research Empirical AI Research
Empirical AI Research
 
[244]로봇이 현실 세계에 대해 학습하도록 만들기
[244]로봇이 현실 세계에 대해 학습하도록 만들기[244]로봇이 현실 세계에 대해 학습하도록 만들기
[244]로봇이 현실 세계에 대해 학습하도록 만들기
 
Николаос Мавридис. От Интерактивных роботов к Человеку-машинному облаку
Николаос Мавридис. От Интерактивных роботов к Человеку-машинному облакуНиколаос Мавридис. От Интерактивных роботов к Человеку-машинному облаку
Николаос Мавридис. От Интерактивных роботов к Человеку-машинному облаку
 
BCII 2016 - Visualizing Complexity
BCII 2016 - Visualizing ComplexityBCII 2016 - Visualizing Complexity
BCII 2016 - Visualizing Complexity
 
Unraveling Information about Deep Learning
Unraveling Information about Deep LearningUnraveling Information about Deep Learning
Unraveling Information about Deep Learning
 
PhD Defence: Leveraging sensing-based interaction for supporting reflection a...
PhD Defence: Leveraging sensing-based interaction for supporting reflection a...PhD Defence: Leveraging sensing-based interaction for supporting reflection a...
PhD Defence: Leveraging sensing-based interaction for supporting reflection a...
 
Mobile collaborative learning dr.azizah25 oct
Mobile collaborative learning dr.azizah25 octMobile collaborative learning dr.azizah25 oct
Mobile collaborative learning dr.azizah25 oct
 

Dernier

Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
 

Dernier (20)

Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
HTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesHTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation Strategies
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 

Innorobo 2016 Keynote - Making robots dream to face open environments

  • 1. Making robots dream to face open environments Stéphane Doncieux
  • 2. What a machine can do YASKAWA BUSHIDO PROJECT / industrial robot vs sword master Deep Blue vs G. Kasparov 1997 Motion Problem resolution
  • 3.
  • 4.
  • 5. Doncieux, S. (to appear) Creativity: A Driver for Research on Robotics in Open Environments, Intellectica Performance Context Robot A Robot B ? ?? ? ?? Known Unknown Unknown
  • 6. How can a robot face a new environment ? 1. Robustness 2. Learning 3. Development
  • 8. Autonomous development Learning 2. Learning Reward High Low A Learning the action to apply in a state to maximize reward. Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning: An introduction. Cambridge: MIT press.
  • 9. 2. Learning continuous actions & states Evaluation Genotype Fitness Random generation Selection Variation 8.3 00110100111 Termination Initial conditionsEvaluation Genotype Phenotype Behavior Environment Fitness Evolutionary Robotics Mouret, J.B., Bredeche, N. et Doncieux S. La robotique évolutionniste Pour la science n°87, Avril-Juin 2015 Doncieux, S., Bredeche, N., Mouret, J.-B., & Eiben, A. E. (2015). Evolutionary Robotics: What, Why, and Where to. Frontiers in Evolutionary Robotics, doi: 10.3389/frobt. 2015.00004
  • 10. A Kober, J., Bagnell, J. a., & Peters, J. (2013). Reinforcement learning in robotics: A survey. The International Journal of Robotics Research, 32(11), 1238–1274. doi:10.1177/0278364913495721 2. Learning The representation is critical ! ???• Reinforcement Learning: fast but requires an efficient representation • Evolutionary Robotics: low level representation, but slow…
  • 11. 3. Development Weng, J. (2004). Developmental robotics : Theory and experiments. International Journal of Humanoid Robotics, 1(2), 199–236. Autonomous development
  • 12. 3. Development Insights from psychology The importance of redescribing knowledge representations «  A specifically human way to gain knowledge is for the mind to exploit internally the information that it has already stored (both innate and acquired), by redescribing its representations or, more precisely, by iteratively re-representing in different representational formats what its internal representations represent » [Karmiloff-Smith 1996] When to restructure and consolidate knowledge ? « Sleep consolidates recent memories and, concomitantly, could allow insight by changing their representational structure. » [Wagner, 2004] Kick-off meeting DREAM, Paris, 26/01/2015
  • 13. Deferred Restructuring of Experience in Autonomous Machines H2020 FET Proactive « Knowing, doing, being » 01/2015-12/2018 http://www.robotsthatdream.eu/ https://twitter.com/robotsthatdream 3. Development Changing representations Daytime experience (large batch) Daytime Consolidated knowledge - task-relevant features - task contexts - abstract knowledge - new motivations No initial policy No single task Motivations: - curiosity - satisfying humans - global mission Behavior exploration Knowledge improvement Knowledge adaptation Small batch Skill Knowledge validation Sequence of learning episodes driven by motivations New situation: -no reprogramming -fast adaptation Knowledge sharing between robots: - better generalization - faster learning Nighttime Dream Collective scale Individual scale Knowledge restructuring Transfer from STM to LTM
  • 14. Learning 10 to 100 times faster Generates examples of behaviours Discrete actions and sensors to consider Passive analysis Representation redescription 2 1 Learning Direct policy search (neuroevolution) Task-agnostic representations Slow learning Limited generalization 3 Learning Discrete reinforcement learning Task-specific representations Fast learning Good generalization
  • 15. Development: bootstrapping simple manipulation skills 1. Day 1: sensori-motor babbling 2. «Night» Learning to manipulate an object in simulation 3.  Day 2 : Back to reality
  • 16. Thank you ! Questions ? stephane.doncieux@upmc.fr https://twitter.com/SDoncieux http://people.isir.upmc.fr/doncieux