SlideShare a Scribd company logo
1 of 73
Download to read offline
Trying to make a
neuroevolved modular robot
step over obstacles
Michael Trouw
supervised by E. Haasdijk 

second reader: B. Weel
12th of August, 2015
Contents
• introduction
• (choice of) subject
• important terms and previous research
• research question
• experiment setup
• results
• conclusion
• discussion
Trying to make a
neuroevolved modular robot
step over obstacles
Neuroevolution
evolving artificial brains
through artificial evolution
+
Modular robots
• reconfigurable
• swarm <> organism
• adapt to specific task
• production cost reduced
• self repair / replace
• more difficult to control
• lower performance on
specific tasks
advantages disadvantages
Modular robots
• Space / deep sea exploration
• Construction (larger architectural systems)
• Box of stuff
• Search and rescue in unstructured environments
applications
Trying to make a
neuroevolved modular robot
step over obstacles
overcoming obstacles
(NASA RASSOR mining robot)
obstacle avoidance
obstacle avoidance
stepping over obstacles
?
Why stepping over
obstacles specifically?
• specific to walking behavior in legged robots
• walking behavior for legged robots is used
frequently
• small literature study/survey > not much ’abstract
motor control’ (turning, reversing direction,
ascending, descending and obstacle evasion).
Important terms
• Central Pattern Generators (CPGs)
• HyperNEAT
• based on NEAT
• compositional pattern producing network (CPPN)
• substrate
• hypercube: x1
* y1
* x2
* y2
Previous research
• HyperNEAT and extensions
• Walking behavior in quadrupeds, hexapods and
octopods
• Locomotion using Central Pattern Generators
• Manually created complex neural networks
• Staged or incremental learning
• HyperNEAT for Locomotion Control in
Modular Robots (2010)
Previous research
• walking behavior in quadrupeds, hexapods and
octopods
2013
2009
2012
Previous research
• CPGs
2011 2014
Previous research
• manually created complex neural networks
2007
Previous research
• staged or incremental learning
2000
Research question
Is it possible to neuroevolve modular robot
organisms that negotiate obstacles and step over
them (without using incremental learning?)
• How can we test if a robotic organism negotiates
obstacles instead of accidentally stepping over them?
• What should a fitness function for the wanted behavior of
stepping over obstacles look like?
Experiment setup
• experiment from HyperNEAT for Locomotion Control in
Modular Robots (2010) was taken and modified
• modular robot of 14 modules
• corridor with obstacles
changes:

• Rings of obstacles instead of corridor with obstacles
• obstacles are randomized before each simulation
• Webots collision detection plugin
• Fitness function modified
• Variants
Experiment setup
Arena experiments
• obstacles surround the robot creature in such
a way that moving around them is impossible.
• 10 repeats of each variant
• 150 generations, 10 individuals
Arena ‘evasion’ experiments
• rings have more space between them
• rings have less obstacles
• 6 repeats of each variant
• 150 generations, 10 individuals
Experiment setup
Fitness function
Stepping over
obstacles
How does one define 'stepping over' ?
• helper: raise legs higher
• very complex award system:
• raise leg near obstacle
• move over same obstacle
• lower leg after obstacle
what is near ?
what if part of obstacle ?
where is ‘after’ ?
Fitness function
Experiment setup
module controller
Experiment setup
• baseline
• no inputs (sensors disabled)
• freeze output
• larger substrate
variations
Experiment setup
freeze output
ωA α
new freeze output.
F
Experiment setup
larger substrate
RS
F
L
B
SL R
B
F
SL R
B
F
RS
F
L
B
RS
F
L
B
front module
right module
bottom module
left module
top module
F
B
RL S
Results
Arena experiments
0 0 0 0
0 0 0 0
Results
Arena ‘evasion’ experiments
Results conclusion
• baseline / no inputs perform nearly the same
• but baseline MBF performs better with less obstacles
• freeze output and larger substrate perform worse then
baseline
• substrate variation does not cover a lot of distance
Recordings
• baseline champions
• baseline `evasion` champions
Discussion
• Interpretation of results
• Answering the research questions
• Critique experiment design
• Suggestions for future work
• Things I’ve learned
Interpretation of results
• no sense of direction (circular movement)
• back away from obstacles
• especially in the case of larger substrate
variant
Research question
• How can we test if a robotic organism negotiates
obstacles instead of accidentally stepping over them?
• comparison in visual analysis: neuroevolution = black
box
• What should an objective fitness function for the wanted
behavior of stepping over obstacles look like?
• no objective fitness function at all !
Research question
Is it possible to neuroevolve modular robot
organisms that negotiate obstacles and step over
them (without using incremental learning?)
• yes, but:
• ‘performance’ is very low
• objective fitness function -> MOEA
• no objective fitness function at all.
Experiment design
critique
• autonomous module control (multiple brains)
• could still be modular
• no information distribution / communication
• less computation
• problem is a MOP: MOEA?
• objectivity issue stays.
Experiment design
critique
Experiment design
critique
• rings of obstacles v.s. scattered obstacles
Suggestions for future
work
• address experiment setup critique
• evolutionary benefit to stepping over
obstacles
• simple maze with obstacle shortcuts
• to resources (resource gathering)
• end of maze (freedom)
Suggestions for future
work
Suggestions for future
work
• Human / 4-legged animal obstacle negotiating behaviors
(combination with models)
• Novelty search
Human behavior
Deceptive problem?
Deceptive problem?
Deceptive problem?
Deceptive problem?
Novelty search
from http://eplex.cs.ucf.edu/noveltysearch/userspage/
• 'A deceptive problem is one in which it is hard to craft an
effective fitness function.’
• 'Novelty search is best suited for deceptive problems'
• great talk by Ken Stanley: http://www.santaferadiocafe.org/
science/2015/03/24/ken-stanley/
Things I’ve learned
• Time spent on implementation
• Spend time thinking abt. workflow: multiple experiments,
data extraction + analyzing.
• Simulation time
• lower ‘iteration’ speed
• triple check all settings before starting experiments
• Webots
• backward compatibility issues
• crashes
• collision bug
• Tooling / Frameworks
Project resources
• source code: https://github.com/michahell/ReactHyperNEAT
• experiment data: http://www.powergeek.nl/files/CPPN%20brainfiles.zip
• presentation:
Acknowledgements
Evert Haasdijk
Berend Weel
Marjeta Markovic
Florian Golemo
Questions ?
Thank you!

More Related Content

Viewers also liked

Protestant reformation 1517
Protestant reformation 1517Protestant reformation 1517
Protestant reformation 1517
rhermanet
 
Practica de l'epiteli bucal.
Practica de l'epiteli bucal.Practica de l'epiteli bucal.
Practica de l'epiteli bucal.
ivan676
 
La cèl·lula
La cèl·lula La cèl·lula
La cèl·lula
ivan676
 
2013 06 12 - présentation de la keynote Web sémantique et Big Data
2013 06 12 - présentation de la keynote Web sémantique et Big Data2013 06 12 - présentation de la keynote Web sémantique et Big Data
2013 06 12 - présentation de la keynote Web sémantique et Big Data
Gabriel KEPEKLIAN
 
Fuzzy logic Based Wall(1)
Fuzzy logic Based Wall(1)Fuzzy logic Based Wall(1)
Fuzzy logic Based Wall(1)
ANSHUMAN SETU
 

Viewers also liked (19)

Grupo delta[1] diapositivas1
Grupo delta[1] diapositivas1Grupo delta[1] diapositivas1
Grupo delta[1] diapositivas1
 
Protestant reformation 1517
Protestant reformation 1517Protestant reformation 1517
Protestant reformation 1517
 
Practica de l'epiteli bucal.
Practica de l'epiteli bucal.Practica de l'epiteli bucal.
Practica de l'epiteli bucal.
 
Ipresantation
IpresantationIpresantation
Ipresantation
 
decollage vostell cbaa
decollage vostell cbaadecollage vostell cbaa
decollage vostell cbaa
 
Gardner, lynn (atlanta_3)[1][1]
Gardner, lynn (atlanta_3)[1][1]Gardner, lynn (atlanta_3)[1][1]
Gardner, lynn (atlanta_3)[1][1]
 
Aquabrowser OPAC à facettes nouvelle génération
Aquabrowser OPAC à facettes nouvelle générationAquabrowser OPAC à facettes nouvelle génération
Aquabrowser OPAC à facettes nouvelle génération
 
DataLift and BigData
DataLift and BigDataDataLift and BigData
DataLift and BigData
 
La cèl·lula
La cèl·lula La cèl·lula
La cèl·lula
 
Infrastructure sémantique pour objets communicants
Infrastructure sémantique pour objets communicantsInfrastructure sémantique pour objets communicants
Infrastructure sémantique pour objets communicants
 
Mapping mobile robotics
Mapping mobile roboticsMapping mobile robotics
Mapping mobile robotics
 
Reseaux sociaux, quelques reperes philosophiques
Reseaux sociaux, quelques reperes philosophiquesReseaux sociaux, quelques reperes philosophiques
Reseaux sociaux, quelques reperes philosophiques
 
2013 06 12 - présentation de la keynote Web sémantique et Big Data
2013 06 12 - présentation de la keynote Web sémantique et Big Data2013 06 12 - présentation de la keynote Web sémantique et Big Data
2013 06 12 - présentation de la keynote Web sémantique et Big Data
 
Fuzzy logic Based Wall(1)
Fuzzy logic Based Wall(1)Fuzzy logic Based Wall(1)
Fuzzy logic Based Wall(1)
 
Aidstalk
AidstalkAidstalk
Aidstalk
 
Pràctica de la densitat
Pràctica de la densitatPràctica de la densitat
Pràctica de la densitat
 
Silbrands V2 Fo Lot2
Silbrands V2 Fo Lot2Silbrands V2 Fo Lot2
Silbrands V2 Fo Lot2
 
Paris
ParisParis
Paris
 
Cell Phone Operated Robot
Cell Phone Operated RobotCell Phone Operated Robot
Cell Phone Operated Robot
 

Similar to Kim presentation

Automated Testing with Databases
Automated Testing with DatabasesAutomated Testing with Databases
Automated Testing with Databases
Stephen Ritchie
 
Unit Testing in SharePoint 2010
Unit Testing in SharePoint 2010Unit Testing in SharePoint 2010
Unit Testing in SharePoint 2010
Chris Weldon
 
The Intersection of Robotics, Search and AI with Solr, MyRobotLab, and Deep L...
The Intersection of Robotics, Search and AI with Solr, MyRobotLab, and Deep L...The Intersection of Robotics, Search and AI with Solr, MyRobotLab, and Deep L...
The Intersection of Robotics, Search and AI with Solr, MyRobotLab, and Deep L...
Lucidworks
 

Similar to Kim presentation (20)

OOP in JS
OOP in JSOOP in JS
OOP in JS
 
Automated Testing but like for PowerShell (April 2012)
Automated Testing but like for PowerShell (April 2012)Automated Testing but like for PowerShell (April 2012)
Automated Testing but like for PowerShell (April 2012)
 
Robotics-ppt.pptx
Robotics-ppt.pptxRobotics-ppt.pptx
Robotics-ppt.pptx
 
Self healing robots
Self healing robotsSelf healing robots
Self healing robots
 
Scala in the Wild
Scala in the WildScala in the Wild
Scala in the Wild
 
Asmod Ali Mondal On Robotics.pdf full details
Asmod Ali Mondal On Robotics.pdf full detailsAsmod Ali Mondal On Robotics.pdf full details
Asmod Ali Mondal On Robotics.pdf full details
 
Asmod Ali Mondal On Robotics.pdf full details
Asmod Ali Mondal On Robotics.pdf full detailsAsmod Ali Mondal On Robotics.pdf full details
Asmod Ali Mondal On Robotics.pdf full details
 
Automated Testing with Databases
Automated Testing with DatabasesAutomated Testing with Databases
Automated Testing with Databases
 
CM20315_01_Intro_Machine_Learning_ap.pptx
CM20315_01_Intro_Machine_Learning_ap.pptxCM20315_01_Intro_Machine_Learning_ap.pptx
CM20315_01_Intro_Machine_Learning_ap.pptx
 
33rd degree
33rd degree33rd degree
33rd degree
 
KATE - a Platform for Machine Learning
KATE - a Platform for Machine LearningKATE - a Platform for Machine Learning
KATE - a Platform for Machine Learning
 
Core java lessons
Core java lessonsCore java lessons
Core java lessons
 
AI Robotics
AI RoboticsAI Robotics
AI Robotics
 
The deep bootstrap framework review
The deep bootstrap framework reviewThe deep bootstrap framework review
The deep bootstrap framework review
 
2009 training - tim m - object oriented programming
2009   training - tim m - object oriented programming2009   training - tim m - object oriented programming
2009 training - tim m - object oriented programming
 
Into the Land of lambda, One Programmer's Journey Into Functional Programming
Into the Land of lambda, One Programmer's Journey Into Functional ProgrammingInto the Land of lambda, One Programmer's Journey Into Functional Programming
Into the Land of lambda, One Programmer's Journey Into Functional Programming
 
Unit Testing in SharePoint 2010
Unit Testing in SharePoint 2010Unit Testing in SharePoint 2010
Unit Testing in SharePoint 2010
 
Robotics, Search and AI with Solr, MyRobotLab, and Deeplearning4j
Robotics, Search and AI with Solr, MyRobotLab, and Deeplearning4jRobotics, Search and AI with Solr, MyRobotLab, and Deeplearning4j
Robotics, Search and AI with Solr, MyRobotLab, and Deeplearning4j
 
The Intersection of Robotics, Search and AI with Solr, MyRobotLab, and Deep L...
The Intersection of Robotics, Search and AI with Solr, MyRobotLab, and Deep L...The Intersection of Robotics, Search and AI with Solr, MyRobotLab, and Deep L...
The Intersection of Robotics, Search and AI with Solr, MyRobotLab, and Deep L...
 
Collision Detection an Overview
Collision Detection an OverviewCollision Detection an Overview
Collision Detection an Overview
 

Recently uploaded

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
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
WSO2
 

Recently uploaded (20)

Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
 
Ransomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdfRansomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdf
 
Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024
 
Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with Milvus
 
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
 
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
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
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
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
 
AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 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
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
 
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...
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
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
 

Kim presentation